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

    Neuronpedia

    INDEX
    Explanations

    мест

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fourth
    -0.06
     nouvelles
    -0.06
    _CHK
    -0.06
     Royale
    -0.06
     second
    -0.06
     external
    -0.06
    REDENTIAL
    -0.06
    _FATAL
    -0.06
     книги
    -0.06
    -strong
    -0.06
    POSITIVE LOGITS
    特
    0.07
     соч
    0.07
    .Link
    0.07
     LOCATION
    0.07
     قن
    0.06
     göz
    0.06
    مق
    0.06
    .spatial
    0.06
    czas
    0.06
     feudal
    0.06
    Act Density 0.005%

    No Known Activations