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

    Neuronpedia

    INDEX
    Explanations

    generated project

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     distrito
    0.49
     necesit
    0.47
     niveles
    0.46
     respecto
    0.46
     masas
    0.44
    alev
    0.44
     conlleva
    0.43
     relacionada
    0.43
     давайте
    0.43
     asociaciones
    0.43
    POSITIVE LOGITS
    Как
    0.51
    С
    0.47
    \
    0.47
    Р
    0.46
    И
    0.46
    AG
    0.45
    Α
    0.44
    Ви
    0.43
    <h4>
    0.43
    Вы
    0.42
    Act Density 0.002%

    No Known Activations