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

    Neuronpedia

    INDEX
    Explanations

    constant velocity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وع
    0.56
    মিক্যাল
    0.51
     planer
    0.49
    總
    0.49
    碼
    0.48
    絭
    0.48
     Crawler
    0.48
    Тре
    0.47
    ة
    0.47
    পদ
    0.47
    POSITIVE LOGITS
     waveform
    0.43
     stormy
    0.43
    `,
    0.42
     fearful
    0.42
     pseudonym
    0.42
     surfboard
    0.41
     (
    0.40
    ::
    0.40
    dressing
    0.40
     shaking
    0.39
    Act Density 0.005%

    No Known Activations