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

    Neuronpedia

    INDEX
    Explanations

    based on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ufs
    0.46
    続
    0.45
    役
    0.44
    schemas
    0.44
     Vero
    0.43
     Thieves
    0.43
     Mavericks
    0.42
     Neue
    0.42
     خطا
    0.42
    ffe
    0.42
    POSITIVE LOGITS
     SD
    0.49
     differs
    0.49
    掙
    0.48
    挣
    0.47
    িয়াছিলেন
    0.46
     orifice
    0.46
     sAlarm
    0.45
     overshoot
    0.44
     ance
    0.44
    ี
    0.44
    Act Density 0.000%

    No Known Activations