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

    Neuronpedia

    INDEX
    Explanations

    hesitation fillers like um or uh

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ina
    1.39
    iendo
    1.38
    硗
    1.35
    iou
    1.34
    iin
    1.34
    ió
    1.30
    u
    1.27
    బడి
    1.26
    OR
    1.25
    i
    1.25
    POSITIVE LOGITS
    س
    1.73
    স
    1.44
    ঙ
    1.44
    וי
    1.43
    র
    1.38
     Arial
    1.34
     thc
    1.34
     assorted
    1.33
    brellas
    1.33
    ড
    1.33
    Act Density 0.034%

    No Known Activations