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

    Neuronpedia

    INDEX
    Explanations

    phrases or words that indicate inquiries or expressions of interest

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

    how about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     död
    -0.37
    ConverterFactory
    -0.34
    ⚠
    -0.32
    `.`
    -0.32
    KURZBESCHREIBUNG
    -0.31
     zw
    -0.31
     HasFactory
    -0.30
     carnet
    -0.30
    transQ
    -0.30
     estekak
    -0.29
    POSITIVE LOGITS
    Fancy
    0.59
     للمعارف
    0.58
    +#+
    0.55
    WireFormatLite
    0.54
    Давайте
    0.54
    ISupport
    0.54
    ladies
    0.53
    Dare
    0.52
    Shall
    0.52
     AssemblyCulture
    0.52
    Act Density 0.003%

    No Known Activations