Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    key mathematical symbols and operations in equations or expressions related to optimization and statistical modeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical equations and relationships involving variables and parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    arg, arg, arg, arg

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंदीखरीदारी
    -0.67
    Autoritní
    -0.63
     autorytatywna
    -0.61
    RenderAtEndOf
    -0.57
     ujednoznacz
    -0.56
    ValueStyle
    -0.55
     esternos
    -0.53
    delwed
    -0.50
    Composable
    -0.49
    Clik
    -0.49
    POSITIVE LOGITS
     highest
    2.04
     largest
    1.90
    highest
    1.85
     lowest
    1.84
    largest
    1.79
     Highest
    1.77
    Highest
    1.76
     longest
    1.75
     tallest
    1.71
     strongest
    1.70
    Act Density 0.652%

    No Known Activations