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

    Neuronpedia

    INDEX
    Explanations

    replay, playback, retrospective reviewing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nection
    0.39
     බ
    0.38
     cuidados
    0.38
    віда
    0.37
    newcommand
    0.37
    ച്ഛ
    0.37
    dsb
    0.36
    ":"","
    0.36
    miers
    0.36
     nou
    0.35
    POSITIVE LOGITS
     replay
    2.39
    replay
    2.11
     playback
    1.61
     retrospect
    1.39
     repl
    1.38
    playback
    1.35
    Playback
    1.33
     recordings
    1.29
     hindsight
    1.27
     retrospective
    1.25
    Act Density 0.030%

    No Known Activations