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

    Neuronpedia

    INDEX
    Explanations

    sentences containing modal verbs or showing uncertainty

    oai_token-act-pair · gemini-2.0-flash

    would

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WithMany
    -0.42
     ensuing
    -0.41
    vrigt
    -0.41
    beforeSend
    -0.40
    celle
    -0.39
    ュ
    -0.39
    سرائيلي
    -0.39
     entourage
    -0.38
     Lame
    -0.37
    esso
    -0.37
    POSITIVE LOGITS
    sizeCache
    1.00
    verwijspagina
    0.93
    Personendaten
    0.87
     disambiguazione
    0.81
    دانشنامهٔ
    0.81
    ViewFeatures
    0.77
    MemoryWarning
    0.74
     autorytatywna
    0.73
    parsedMessage
    0.72
    Pautan
    0.71
    Act Density 1.311%

    No Known Activations