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

    Neuronpedia

    INDEX
    Explanations

    off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     đáo
    -0.07
     Front
    -0.06
     ordinal
    -0.06
    jd
    -0.06
     thiên
    -0.06
    .but
    -0.06
    _checksum
    -0.06
     неп
    -0.06
     техніч
    -0.06
    (reverse
    -0.06
    POSITIVE LOGITS
    .X
    0.08
    خ
    0.06
    ू
    0.06
    Ens
    0.06
    Input
    0.06
    ласти
    0.06
    ovy
    0.06
    هاي
    0.06
     Zimmer
    0.05
     avez
    0.05
    Act Density 0.000%

    No Known Activations