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

    Neuronpedia

    INDEX
    Explanations

    effective

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wilkinson
    -0.09
     అమ
    -0.08
     beneath
    -0.08
     Am
    -0.07
     évo
    -0.07
     تخ
    -0.07
     Hubbard
    -0.07
     ответственность
    -0.07
     bers
    -0.07
     fino
    -0.07
    POSITIVE LOGITS
     eficaz
    0.11
    率
    0.11
     ביותר
    0.09
    益
    0.08
    、安全
    0.08
     efic
    0.08
     julọ
    0.08
    -packed
    0.08
     enough
    0.08
     quả
    0.08
    Act Density 0.030%

    No Known Activations