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

    Neuronpedia

    INDEX
    Explanations

    urgent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    打扮
    -0.07
    />↵↵
    -0.07
     boasting
    -0.07
    Sweet
    -0.06
     winners
    -0.06
    缺少
    -0.06
    .Dict
    -0.06
    增
    -0.06
     순
    -0.06
    スト
    -0.06
    POSITIVE LOGITS
     occured
    0.08
     осуществ
    0.08
     Fault
    0.08
    指挥部
    0.08
    Cnt
    0.07
    几点
    0.07
    _seg
    0.07
    �
    0.07
     случа
    0.07
     confidential
    0.07
    Act Density 0.015%

    No Known Activations