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

    Neuronpedia

    INDEX
    Explanations

    rehearse, rehearsal, rehearsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ীষ
    0.45
    じて
    0.43
     Redis
    0.41
     rediscover
    0.40
     redis
    0.39
    সুমে
    0.39
     sphinx
    0.39
    Redis
    0.38
    UpDown
    0.38
     pud
    0.38
    POSITIVE LOGITS
     rehearsals
    1.88
     rehearsal
    1.84
     rehears
    1.84
     rehearse
    1.81
     Reh
    0.84
    演
    0.82
     rehe
    0.80
     reh
    0.80
     ensayo
    0.74
     ره
    0.72
    Act Density 0.001%

    No Known Activations