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

    Neuronpedia

    INDEX
    Explanations

    peak times, rates, or highest points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    庥
    0.38
     prens
    0.38
    gados
    0.37
    ន្ធ
    0.37
     password
    0.37
    🚚
    0.37
    瑠
    0.36
    𝐃
    0.36
    囁
    0.36
    思議
    0.36
    POSITIVE LOGITS
     peak
    4.38
    Peak
    3.84
     Peak
    3.81
    peak
    3.70
     peaks
    3.64
     peaked
    3.39
    ピーク
    3.28
     peaking
    3.19
    峰
    3.14
    peaks
    3.06
    Act Density 0.080%

    No Known Activations