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

    Neuronpedia

    INDEX
    Explanations

    agreement/acceptance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.64
    bolista
    -0.50
    tanleria
    -0.49
    InitStruct
    -0.48
    出版年
    -0.47
    PreferredItem
    -0.47
    msgTypes
    -0.46
     vPvB
    -0.46
    Kew
    -0.46
    exitRule
    -0.45
    POSITIVE LOGITS
    abestanden
    0.65
    NotBe
    0.65
     to
    0.63
     onPostExecute
    0.61
    ])*
    0.58
    öng
    0.54
     pulumi
    0.54
     not
    0.52
    InputModule
    0.52
    outé
    0.51
    Act Density 0.002%

    No Known Activations