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

    Neuronpedia

    INDEX
    Explanations

    Lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    最佳
    -0.08
    ଡ
    -0.08
    Best
    -0.08
    ନ
    -0.08
     best
    -0.07
     导
    -0.07
    onte
    -0.07
    Public
    -0.07
     bots
    -0.07
     安
    -0.07
    POSITIVE LOGITS
     хәл
    0.10
     можа
    0.09
    fico
    0.09
     საშუალებას
    0.08
     отсутствие
    0.08
     negatif
    0.08
    ocu
    0.08
     كيلو
    0.08
     ხდება
    0.08
     flwyddyn
    0.08
    Act Density 0.091%

    No Known Activations