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

    Neuronpedia

    INDEX
    Explanations

    Engine demos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ay
    0.62
    ul
    0.61
    ov
    0.56
    il
    0.55
    ai
    0.54
    et
    0.53
    ita
    0.51
    en
    0.50
    os
    0.50
    ig
    0.49
    POSITIVE LOGITS
    茈
    0.55
     dotycz
    0.51
    ට්ට
    0.51
    எ
    0.49
     cero
    0.49
     cargas
    0.48
    पी
    0.47
    এ
    0.47
    ఆ
    0.47
     entorno
    0.47
    Act Density 0.001%

    No Known Activations