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

    Neuronpedia

    INDEX
    Explanations

    absolute minimum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     columnspan
    0.65
     لوبی
    0.64
    来越
    0.64
     हजारों
    0.63
    ֱ
    0.62
     الحره
    0.62
    特定の
    0.61
    ncoder
    0.61
     привод
    0.61
     അറിയ
    0.61
    POSITIVE LOGITS
     minimum
    2.65
    minimum
    2.45
     Minimum
    2.33
    Minimum
    2.28
     mínimo
    2.10
     minimo
    1.98
     minima
    1.95
    至少
    1.93
     최소
    1.87
     минимум
    1.86
    Act Density 0.128%

    No Known Activations