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

    Neuronpedia

    INDEX
    Explanations

    Error messages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⮞
    -0.07
    -parent
    -0.07
    emp
    -0.07
    weakSelf
    -0.07
    行业中
    -0.07
     Side
    -0.06
    ories
    -0.06
    ANDING
    -0.06
    ellido
    -0.06
     ice
    -0.06
    POSITIVE LOGITS
     ------
    0.07
     experiments
    0.07
    感じ
    0.07
    ጁ
    0.06
     sina
    0.06
     vợ
    0.06
     노력
    0.06
     fortunate
    0.06
    бир
    0.06
    'class
    0.06
    Act Density 0.088%

    No Known Activations