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

    Neuronpedia

    INDEX
    Explanations

    prompt style

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2.03
    Esto
    1.91
     Конечно
    1.81
    দিন
    1.72
    缆
    1.66
     सहस्त्र
    1.66
    وی
    1.63
    णिज्य
    1.62
     putchar
    1.62
    ́u
    1.60
    POSITIVE LOGITS
     outfitted
    1.74
     foci
    1.72
     peril
    1.69
    i
    1.68
    м
    1.66
    iin
    1.65
     overdue
    1.65
     tumbler
    1.65
    мб
    1.63
    साथ
    1.60
    Act Density 0.000%

    No Known Activations