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

    Neuronpedia

    INDEX
    Explanations

    specific formatting or structures in text, including references to functions, categories, or definitions in a programming context

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

    Code, math, or numbers within parentheses

    np_acts-logits-general · gemini-2.0-flash

    whereas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.54
    MarshalTo
    -0.51
    --*/
    -0.49
     comuniques
    -0.47
     Italijanski
    -0.46
    лтемелер
    -0.45
    AccessorTable
    -0.44
     समीक्षाएं
    -0.43
     الحره
    -0.43
    .)}
    -0.42
    POSITIVE LOGITS
     whereas
    0.43
    Whereas
    0.41
    whereas
    0.40
    Réalisation
    0.40
    ReusableCell
    0.40
    EClass
    0.37
     Whereas
    0.37
    article
    0.37
    ThemeOverlay
    0.36
     الدولى
    0.35
    Act Density 1.461%

    No Known Activations