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

    Neuronpedia

    INDEX
    Explanations

    the answer behind it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     گرفتن
    0.52
     postérieurs
    0.52
    ဟ
    0.50
    ioribus
    0.49
    ي
    0.49
    Przeczytaj
    0.49
    i
    0.49
    Virat
    0.48
    Spar
    0.48
    Veja
    0.47
    POSITIVE LOGITS
    ка
    0.49
     Kindle
    0.48
     PYTHON
    0.48
     Python
    0.47
     Pol
    0.46
     Cancer
    0.46
     HIV
    0.46
     May
    0.46
     Fac
    0.46
     Fun
    0.45
    Act Density 0.000%

    No Known Activations