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

    Neuronpedia

    INDEX
    Explanations

    consult with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aftermarket
    0.84
     конкурса
    0.83
     प्रश्नों
    0.83
     pertanyaan
    0.82
     frågor
    0.81
     방법에
    0.80
     nightlife
    0.77
     Forecasting
    0.76
     perguntas
    0.76
     〢
    0.76
    POSITIVE LOGITS
    times
    0.72
     sama
    0.70
     coils
    0.65
    piece
    0.63
    威力
    0.60
    s
    0.60
    or
    0.59
    No
    0.58
    sama
    0.58
     العاشر
    0.58
    Act Density 0.007%

    No Known Activations