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

    Neuronpedia

    INDEX
    Explanations

    serial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PO
    -0.08
     امکان
    -0.06
    Although
    -0.06
    方案
    -0.06
    Bre
    -0.06
    _CF
    -0.06
     RES
    -0.06
    rias
    -0.06
    IGNAL
    -0.06
    凝
    -0.06
    POSITIVE LOGITS
     книги
    0.08
     Michelle
    0.06
     Johannesburg
    0.06
     Near
    0.06
     China
    0.06
     Democrat
    0.06
     μας
    0.06
     decorators
    0.06
    季
    0.06
    .Anchor
    0.06
    Act Density 0.002%

    No Known Activations