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

    Neuronpedia

    INDEX
    Explanations

    court orders

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .problem
    -0.08
    ¼
    -0.07
    :@
    -0.07
    矿泉水
    -0.07
    -primary
    -0.07
     locus
    -0.07
    PY
    -0.06
     màu
    -0.06
    商
    -0.06
    硫酸
    -0.06
    POSITIVE LOGITS
     усл
    0.07
    넘
    0.07
    热潮
    0.07
    过剩
    0.07
    компон
    0.07
    шу
    0.07
    Strength
    0.07
     dwell
    0.07
    شهد
    0.07
    _STR
    0.07
    Act Density 0.001%

    No Known Activations