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

    Neuronpedia

    INDEX
    Explanations

    configuraciones específicas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     який
    0.86
     हुईं
    0.82
     bellissimo
    0.81
     lindos
    0.77
    ultimo
    0.73
     său
    0.73
     quello
    0.73
     các
    0.73
     celý
    0.73
     suoi
    0.70
    POSITIVE LOGITS
     herself
    0.86
     de
    0.78
     específica
    0.78
     significativa
    0.75
     científica
    0.74
    ográfica
    0.71
     المختلفة
    0.68
     المحلية
    0.68
     الجديدة
    0.67
     positiva
    0.67
    Act Density 0.508%

    No Known Activations