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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions related to formal definitions or theorems

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

    Mathematical notation with parentheses and subscripts

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "
    -0.56
    Демо
    -0.56
    </
    -0.56
     recor
    -0.54
    asson
    -0.54
    rungsseite
    -0.53
     -->
    -0.51
    $_['
    -0.50
    ...</
    -0.50
    )
    -0.50
    POSITIVE LOGITS
     itſelf
    0.70
     Theſe
    0.63
     myſelf
    0.63
     Efq
    0.62
    CloseOperation
    0.60
    GRAFÍA
    0.60
     disparu
    0.59
    soever
    0.58
     termica
    0.58
     frattempo
    0.57
    Act Density 0.840%

    No Known Activations