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

    Neuronpedia

    INDEX
    Explanations

    Software development practices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tility
    -0.08
     ER
    -0.07
    (chip
    -0.07
    ств
    -0.07
    ckill
    -0.07
     subscribers
    -0.07
    _CAL
    -0.07
     pistols
    -0.07
    (expression
    -0.07
    的地步
    -0.06
    POSITIVE LOGITS
    큰
    0.07
    ']*
    0.07
    氛围
    0.07
     Hội
    0.07
    江西省
    0.07
    內部
    0.07
    可怕
    0.07
    Rate
    0.07
    左边
    0.07
    时常
    0.07
    Act Density 0.024%

    No Known Activations