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

    Neuronpedia

    INDEX
    Explanations

    immediate disruption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     점점
    0.73
    越来越
    0.68
     ఇటీవల
    0.57
     occasionally
    0.53
     lately
    0.51
     continually
    0.50
    越來越
    0.49
     occasional
    0.49
     ఇటీ
    0.49
     சமீப
    0.48
    POSITIVE LOGITS
     immediately
    1.42
     instantly
    1.41
    Immediately
    1.34
     immediatamente
    1.34
     inmediatamente
    1.32
    immediately
    1.32
     Immediately
    1.29
     imediatamente
    1.29
     suddenly
    1.25
    立刻
    1.25
    Act Density 0.018%

    No Known Activations