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

    Neuronpedia

    INDEX
    Explanations

    impact on society

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _stat
    -0.07
    �
    -0.06
    _ranges
    -0.06
     moments
    -0.06
     contents
    -0.06
     Roh
    -0.06
    цієн
    -0.06
     spoken
    -0.06
     گفته
    -0.06
    ishment
    -0.06
    POSITIVE LOGITS
     upt
    0.06
    Using
    0.06
    !?
    0.06
    HE
    0.06
    强
    0.06
     абсолют
    0.06
    'C
    0.06
    sar
    0.06
    ΑΔ
    0.06
    -append
    0.06
    Act Density 0.004%

    No Known Activations