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

    Neuronpedia

    INDEX
    Explanations

    Urgent/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ם
    0.87
    ر
    0.83
     ع
    0.72
     immers
    0.70
     stesso
    0.70
    sächlich
    0.69
    ната
    0.68
    יו
    0.67
     ску
    0.67
    ادية
    0.67
    POSITIVE LOGITS
    AHN
    0.82
    ASS
    0.79
     Dirección
    0.79
     abrang
    0.77
     Kernel
    0.76
    ്രി
    0.74
     Engines
    0.73
     windmill
    0.71
     Reactor
    0.70
     Servicio
    0.70
    Act Density 0.000%

    No Known Activations