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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and inequalities involving sums and products

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

    Mathematical expressions with subscripts

    np_acts-logits-general · gemini-2.0-flash

    mathematical indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.67
    تقاوى
    -0.62
    liferay
    -0.56
    {}".
    -0.53
    enderror
    -0.52
    })$}
    -0.51
    KURZBESCHREIBUNG
    -0.51
    Rptr
    -0.51
     riêng
    -0.47
    bull
    -0.47
    POSITIVE LOGITS
    substack
    1.14
    IsContent
    0.78
     autorytatywna
    0.73
     zvuky
    0.67
     Saltar
    0.66
    AnimationsModule
    0.63
     muligt
    0.62
     épaules
    0.62
     "..\..\..\
    0.62
     Suivez
    0.61
    Act Density 0.594%

    No Known Activations