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

    Neuronpedia

    INDEX
    Explanations

    words indicating variations or inclusivity in categories

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

    quantifiers and unspecified nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.69
     mutiara
    -0.64
     الرياضيه
    -0.62
    ammans
    -0.59
    djangoproject
    -0.58
    yarnpkg
    -0.56
     ThemeData
    -0.54
     defaultstate
    -0.54
    BitConverter
    -0.54
    ähteet
    -0.54
    POSITIVE LOGITS
     of
    0.57
     Of
    0.51
     OF
    0.48
    Of
    0.46
     ofthe
    0.43
    of
    0.40
    OfClass
    0.40
     của
    0.37
     cua
    0.36
    OfThe
    0.36
    Act Density 0.070%

    No Known Activations