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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vecs
    -0.06
    반
    -0.06
    sure
    -0.06
    Degrees
    -0.06
     Rage
    -0.06
    这里
    -0.06
    ابعة
    -0.06
     pulls
    -0.06
    ическая
    -0.06
    enerating
    -0.06
    POSITIVE LOGITS
     };↵↵
    0.07
     financ
    0.07
     فعال
    0.06
    .bp
    0.06
     sorun
    0.06
     підготов
    0.06
    ghan
    0.06
     ترک
    0.06
    (isolate
    0.06
    15
    0.06
    Act Density 0.224%

    No Known Activations