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

    Neuronpedia

    INDEX
    Explanations

    response

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -op
    -0.07
    (f
    -0.07
    (T
    -0.07
    ክ
    -0.07
     satisfied
    -0.07
    ⴽ
    -0.07
    .getY
    -0.07
    憺
    -0.07
    _CHECK
    -0.07
    (default
    -0.07
    POSITIVE LOGITS
    ,proto
    0.08
     Sting
    0.08
    高品质
    0.07
    文化
    0.07
    文化的
    0.07
    与时俱进
    0.07
     Seeing
    0.06
     toxin
    0.06
    /photo
    0.06
     плит
    0.06
    Act Density 0.008%

    No Known Activations