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

    Neuronpedia

    INDEX
    Explanations

    common phrases or templates in written dialogues

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

    Numerical computations and formulas

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jeografia
    -0.41
    tagHelperRunner
    -0.40
     Roskov
    -0.30
    延
    -0.29
    +#+#
    -0.29
    SARA
    -0.28
     třeba
    -0.28
    qtype
    -0.28
     Italijanski
    -0.28
    PAI
    -0.27
    POSITIVE LOGITS
     مشين
    0.66
     Monfieur
    0.61
    UpInside
    0.56
    KommentareTeilen
    0.56
     desmotivaciones
    0.55
     MainAxisSize
    0.55
    RectangleBorder
    0.53
    CloseOperation
    0.53
    RenderAtEndOf
    0.53
    URLException
    0.53
    Act Density 1.425%

    No Known Activations