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

    Neuronpedia

    INDEX
    Explanations

    certo, cuidado, copia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lub
    0.72
    Kep
    0.71
    ✚
    0.68
    Ben
    0.66
    cursive
    0.65
    DING
    0.63
    Additive
    0.63
    KING
    0.62
     nak
    0.62
    CoV
    0.62
    POSITIVE LOGITS
    és
    0.78
    ál
    0.75
    ít
    0.75
    iste
    0.73
     what
    0.71
    ключение
    0.71
     último
    0.70
     cuanto
    0.70
     está
    0.69
    á
    0.69
    Act Density 0.026%

    No Known Activations