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

    Neuronpedia

    INDEX
    Explanations

    common descriptors of typical scenarios or experiences

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

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    expected in, experienced by, inappropriate for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     istrinya
    -0.41
    flexDirection
    -0.40
    getRuntime
    -0.40
    ળ
    -0.39
    وای
    -0.39
    Enumerated
    -0.38
     opérés
    -0.38
    gow
    -0.37
    ConverterFactory
    -0.37
     maks
    -0.37
    POSITIVE LOGITS
     typical
    1.14
     ddelweddau
    1.07
    typical
    0.95
     autorytatywna
    0.90
    HideFlags
    0.89
     típico
    0.89
     Typical
    0.88
     típica
    0.88
    Typical
    0.88
    AsUp
    0.88
    Act Density 0.535%

    No Known Activations