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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions, particularly dealing with functions and variables

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

    condition if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.54
     contextLoads
    -0.51
     Administrativna
    -0.47
    twimg
    -0.46
    aibo
    -0.43
    matchCondition
    -0.42
    tagHelperRunner
    -0.41
    раздо
    -0.40
    IsMutable
    -0.40
    WebVitals
    -0.40
    POSITIVE LOGITS
     if
    0.68
     If
    0.65
    IfNot
    0.63
     अगर
    0.63
    如果有
    0.62
     IF
    0.60
    如果您
    0.59
    如果是
    0.56
    如果不
    0.56
    如果你
    0.55
    Act Density 0.121%

    No Known Activations