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

    Neuronpedia

    INDEX
    Explanations

    references to functions and events in code snippets

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

    function calls or event handlers

    np_acts-logits-general · gemini-2.0-flash

    function calls and callbacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.56
    venge
    -0.56
     Apo
    -0.50
    ">//
    -0.48
    strophic
    -0.48
    vete
    -0.47
    ✭✭
    -0.47
    ESPEC
    -0.47
     Maggiore
    -0.46
    bulo
    -0.46
    POSITIVE LOGITS
    Invoke
    0.71
     applied
    0.66
    MethodManager
    0.60
    call
    0.60
    guém
    0.58
    applied
    0.57
     executed
    0.57
     실행
    0.57
    MessageTagHelper
    0.57
     ویکی‌پدیای
    0.56
    Act Density 0.108%

    No Known Activations