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

    Neuronpedia

    INDEX
    Explanations

    sections or elements in data that involve figures, equations, or mathematical formatting

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

    sections or headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TextInputType
    -0.76
    -0.75
    featureID
    -0.75
    principalColumn
    -0.73
     typelib
    -0.73
    SharedCtor
    -0.71
    новниш
    -0.69
     bezeichneter
    -0.68
     للمعارف
    -0.67
     disambiguazione
    -0.67
    POSITIVE LOGITS
    I
    0.43
     notare
    0.38
    C
    0.36
    R
    0.36
    ish
    0.36
    i
    0.36
    ICom
    0.36
    DIV
    0.35
    on
    0.35
     Saat
    0.35
    Act Density 0.009%

    No Known Activations