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

    Neuronpedia

    INDEX
    Explanations

    risk and reward

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     opções
    0.46
    ften
    0.41
     velit
    0.41
     smlou
    0.40
    uales
    0.40
     THAT
    0.40
     mogelijkheden
    0.40
    etz
    0.39
    avalt
    0.39
    ne
    0.39
    POSITIVE LOGITS
     бана
    0.45
    Ин
    0.45
     риск
    0.44
     Россия
    0.44
     Укра
    0.42
     barber
    0.42
     бан
    0.42
    動力
    0.42
    гра
    0.42
     वॉटर
    0.42
    Act Density 0.000%

    No Known Activations