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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     {};
    -0.08
     Compliance
    -0.07
     �
    -0.07
     Lingu
    -0.07
     Shape
    -0.07
    .Pre
    -0.07
     compliance
    -0.06
     Graduate
    -0.06
    lis
    -0.06
     Brut
    -0.06
    POSITIVE LOGITS
    σταση
    0.06
    قال
    0.06
    のか
    0.06
    ея
    0.06
    까
    0.06
    ومات
    0.06
     sle
    0.06
    ουμε
    0.06
    erged
    0.06
    .Customer
    0.06
    Act Density 0.182%

    No Known Activations