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

    Neuronpedia

    INDEX
    Explanations

    connections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _estimators
    -0.07
     노출
    -0.06
     attention
    -0.06
     tolik
    -0.06
    ในท
    -0.06
    vironments
    -0.06
     선택
    -0.06
    �
    -0.06
    لل
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     сч
    0.07
     با
    0.07
     ale
    0.06
    保
    0.06
    ammers
    0.06
     Sultan
    0.06
     bachelor
    0.06
    Pe
    0.06
    PE
    0.06
    /code
    0.06
    Act Density 0.049%

    No Known Activations