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

    Neuronpedia

    INDEX
    Explanations

    codes, dates, and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vel
    0.63
    ೋಜನ
    0.61
    zy
    0.61
     of
    0.61
     by
    0.60
    w
    0.60
    ert
    0.59
    finite
    0.59
    fix
    0.58
    g
    0.58
    POSITIVE LOGITS
    し
    0.89
    狒
    0.70
    iciência
    0.68
     вариан
    0.68
    ного
    0.67
    ления
    0.67
    માં
    0.66
     pasajeros
    0.66
     necessário
    0.66
     padrões
    0.64
    Act Density 0.099%

    No Known Activations