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

    Neuronpedia

    INDEX
    Explanations

    at an [adjective] rate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    体重
    0.52
    tbody
    0.43
    sklär
    0.42
     Vanilla
    0.41
    őt
    0.41
    朹
    0.40
     ढांचे
    0.39
    栊
    0.38
    在哪里
    0.38
     جہاں
    0.37
    POSITIVE LOGITS
     rate
    1.20
     rates
    1.03
    rate
    0.98
     Rate
    0.96
     pace
    0.95
     accelerated
    0.92
    Rate
    0.90
     RATE
    0.88
    rates
    0.84
     speed
    0.83
    Act Density 0.014%

    No Known Activations