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

    Neuronpedia

    INDEX
    Explanations

    breaks and pauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StartsWith
    0.37
    잣
    0.36
    ิศ
    0.36
    argeon
    0.34
    躋
    0.34
    ক্ক
    0.33
    scaron
    0.33
    riente
    0.32
    </footer>
    0.32
     Shay
    0.32
    POSITIVE LOGITS
     pauses
    2.97
     pause
    2.91
     pausa
    2.70
     Pause
    2.59
    pause
    2.53
     pausing
    2.52
    Pause
    2.47
     paused
    2.44
     breaks
    2.27
     пау
    2.05
    Act Density 0.086%

    No Known Activations