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

    Neuronpedia

    INDEX
    Explanations

    opted for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    0.93
    g
    0.88
    l
    0.81
    ون
    0.80
    er
    0.80
    an
    0.80
    (
    0.77
    ב
    0.77
    sg
    0.77
    ad
    0.74
    POSITIVE LOGITS
     перед
    0.83
     rehabilitación
    0.82
     avanzando
    0.81
     устройства
    0.81
     mecánica
    0.80
     dentro
    0.79
     рублей
    0.79
     план
    0.79
    та
    0.79
     enfrentar
    0.78
    Act Density 0.001%

    No Known Activations