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

    Neuronpedia

    INDEX
    Explanations

    timestamp / date and time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Burmese
    0.73
     Bile
    0.71
     그
    0.71
     pound
    0.71
     sexual
    0.70
     trump
    0.69
     cultural
    0.69
     intensification
    0.68
     embracing
    0.68
    sexual
    0.68
    POSITIVE LOGITS
    时刻
    0.95
    凌晨
    0.89
     madrugada
    0.81
     രാവിലെ
    0.80
    获取
    0.80
    此时
    0.79
     lúc
    0.78
     오전
    0.78
    上午
    0.78
    算法
    0.78
    Act Density 0.053%

    No Known Activations