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

    Neuronpedia

    INDEX
    Explanations

    potential outcomes under conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    象棋
    0.54
    漃
    0.50
     ہے
    0.49
    tLogRow
    0.48
    鋆
    0.48
    HTTPS
    0.48
    oomla
    0.47
    薁
    0.46
    фы
    0.45
    คาเด
    0.44
    POSITIVE LOGITS
     physiologically
    0.49
     shocks
    0.48
     objectively
    0.48
     superhuman
    0.47
     contemporaneous
    0.46
     conditions
    0.46
     predators
    0.46
     comparable
    0.46
    0.46
     physiology
    0.45
    Act Density 0.011%

    No Known Activations