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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific phrases related to instructions or actions

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

    Saznajte kako

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    новништво
    -0.58
    IntoConstraints
    -0.52
    ConverterFactory
    -0.47
    iff
    -0.45
     FontWeight
    -0.45
    BindView
    -0.43
    äksi
    -0.43
    iibo
    -0.42
     Crews
    -0.41
    RectangleBorder
    -0.41
    POSITIVE LOGITS
    Przeczytaj
    1.88
    Citiți
    0.88
     nalazi
    0.79
     Wikiseite
    0.68
     ostavi
    0.57
    adaptiveStyles
    0.54
    Rüyada
    0.52
    Читати
    0.51
    Diwedd
    0.51
    Kontrola
    0.50
    Act Density 0.000%

    No Known Activations