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

    Neuronpedia

    INDEX
    Explanations

    cohort

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Given
    -0.07
    טענות
    -0.07
     funk
    -0.07
     replies
    -0.07
    !’
    -0.07
     asks
    -0.07
     женщин
    -0.06
    مز
    -0.06
    از
    -0.06
    Samples
    -0.06
    POSITIVE LOGITS
    تفاص
    0.09
    _depart
    0.08
     rehab
    0.07
     Ibid
    0.07
     jersey
    0.07
    技術
    0.07
    .configuration
    0.07
    這裡
    0.07
     affili
    0.07
    ちら
    0.06
    Act Density 0.005%

    No Known Activations