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

    Neuronpedia

    INDEX
    Explanations

    Exploitation, behaviors, explosion, method, war

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     появляются
    0.86
    ưởng
    0.84
     केले
    0.83
     Reasons
    0.81
     появляется
    0.81
     знаю
    0.79
     불구
    0.79
     प्रेरित
    0.78
     Roshelle
    0.78
     얘는
    0.77
    POSITIVE LOGITS
    ה
    1.04
    ک
    0.89
    ወስ
    0.84
    selves
    0.80
    ٖ
    0.78
    І
    0.77
    elor
    0.76
     rul
    0.76
    ی
    0.76
    است
    0.75
    Act Density 0.000%

    No Known Activations