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

    Neuronpedia

    INDEX
    Explanations

    negative qualifiers and conjunctions

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

    following conjunctions (but, and, or, as)

    np_acts-logits-general · gemini-2.0-flash

    not only... but also

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     चीज़ों
    -0.74
    TypedDataSet
    -0.73
    SizeMode
    -0.66
    getSeconds
    -0.64
     isother
    -0.63
     autorytatywna
    -0.63
    RenderAtEndOf
    -0.62
    σθαι
    -0.62
    DAOImpl
    -0.62
    ähne
    -0.61
    POSITIVE LOGITS
     of
    0.73
     also
    0.65
     by
    0.64
     terhadap
    0.60
     else
    0.58
     for
    0.58
     también
    0.55
     from
    0.54
     with
    0.53
     também
    0.53
    Act Density 1.147%

    No Known Activations