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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     podem
    -0.08
     السي
    -0.07
     kaybet
    -0.07
     معمول
    -0.07
    ثل
    -0.07
     doğru
    -0.06
    _PER
    -0.06
     σε
    -0.06
    مین
    -0.06
     جست
    -0.06
    POSITIVE LOGITS
    onu
    0.07
    eating
    0.06
    quipment
    0.06
    csrf
    0.06
    (validation
    0.06
    _epoch
    0.06
     grocery
    0.06
    (n
    0.06
     Vertex
    0.06
    >>,
    0.06
    Act Density 0.101%

    No Known Activations