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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculations and operations

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

    Numerical calculations and fractions

    np_acts-logits-general · gemini-2.0-flash

    text editor or text formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.77
    -0.59
     enfans
    -0.54
    __(/*!
    -0.53
    ANTLR
    -0.52
     للمعارف
    -0.52
    Personensuche
    -0.52
    RenderAtEndOf
    -0.52
     مشين
    -0.51
    OGND
    -0.50
    POSITIVE LOGITS
     außerdem
    0.42
    diak
    0.42
    lio
    0.38
    lx
    0.37
    aulted
    0.37
    FailureListener
    0.37
    ECD
    0.36
    alie
    0.35
     others
    0.35
    dess
    0.35
    Act Density 1.394%

    No Known Activations