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

    Neuronpedia

    INDEX
    Explanations

    HTML and XML syntax elements

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

    field select via those value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.83
     propOrder
    -0.66
     nakalista
    -0.65
    msgTypes
    -0.64
    :✨
    -0.62
     صوتيه
    -0.60
     Италијани
    -0.57
    exitRule
    -0.57
    printStackTrace
    -0.56
     &___
    -0.56
    POSITIVE LOGITS
     rather
    0.42
    rather
    0.36
    endaft
    0.35
     sliding
    0.34
     a
    0.33
     vielmehr
    0.33
    strides
    0.33
     medesimo
    0.31
     bellows
    0.30
     spirits
    0.30
    Act Density 0.001%

    No Known Activations