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

    Neuronpedia

    INDEX
    Explanations

    Violence and death

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    民事
    -0.08
     occurring
    -0.07
    放出
    -0.07
    victim
    -0.07
    Buy
    -0.07
     Dealer
    -0.07
    生活中
    -0.06
    ادي
    -0.06
    $",
    -0.06
     complying
    -0.06
    POSITIVE LOGITS
     harga
    0.07
    𫄧
    0.07
     wybra
    0.07
     SPF
    0.07
     theatrical
    0.07
    Jul
    0.07
     marg
    0.07
    moire
    0.07
     poj
    0.07
    羧
    0.06
    Act Density 0.037%

    No Known Activations