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

    Neuronpedia

    INDEX
    Explanations

    matching criteria

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     posibilidad
    0.89
     medición
    0.88
     а
    0.87
     assistenza
    0.84
     innovación
    0.82
     графика
    0.81
    隀
    0.81
     integración
    0.80
     financiación
    0.80
     información
    0.80
    POSITIVE LOGITS
    e
    1.09
    le
    1.02
     It
    0.94
     '
    0.93
     If
    0.90
    re
    0.89
    ם
    0.89
    ל
    0.88
    3
    0.88
    ل
    0.88
    Act Density 0.015%

    No Known Activations