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

    Neuronpedia

    INDEX
    Explanations

    equality or assignment operators

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

    Tokens followed by equal signs

    np_acts-logits-general · gemini-2.0-flash

    assignment and comparison operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     архивлан
    -0.67
     study
    -0.61
    kirch
    -0.59
    خواندن
    -0.59
     NDEBUG
    -0.58
    Slides
    -0.57
    expandindo
    -0.57
     ustedes
    -0.57
     esternos
    -0.57
     ${({
    -0.56
    POSITIVE LOGITS
    /=
    1.28
     CreateTagHelper
    1.06
    .=
    0.84
    >=</
    0.83
    ArgsConstructor
    0.82
    _=
    0.81
     $=\
    0.76
    :=
    0.73
     Zapata
    0.69
    //=
    0.69
    Act Density 0.514%

    No Known Activations