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

    Neuronpedia

    INDEX
    Explanations

    elements of programming code and their constructs

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

    mathematical formatting and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <thead>
    -0.40
     accion
    -0.39
     fuck
    -0.38
    Aktualisiert
    -0.36
    pexpr
    -0.36
    GetAxis
    -0.36
    kmale
    -0.36
    seros
    -0.36
    ECONDS
    -0.35
     Acc
    -0.35
    POSITIVE LOGITS
     createSlice
    0.80
    WebVitals
    0.56
    OGND
    0.54
     للمعارف
    0.46
     validamos
    0.42
    BeginContext
    0.41
    isContained
    0.40
    Geplaatst
    0.40
    styleable
    0.39
     Olli
    0.39
    Act Density 0.001%

    No Known Activations