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

    Neuronpedia

    INDEX
    Explanations

    variables and their assignments in code

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

    value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.58
    AndEndTag
    -0.56
    kasse
    -0.47
    atother
    -0.47
    TintMode
    -0.45
    AnchorTagHelper
    -0.44
    jfree
    -0.43
    omla
    -0.43
    Malley
    -0.42
    ‟
    -0.42
    POSITIVE LOGITS
     value
    0.73
     valeur
    0.67
     valore
    0.64
     valori
    0.63
     values
    0.63
    value
    0.63
     Valores
    0.63
     valores
    0.63
     Value
    0.62
     valeurs
    0.62
    Act Density 0.073%

    No Known Activations