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

    Neuronpedia

    INDEX
    Explanations

    saving enough

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     baik
    0.43
     perils
    0.42
    ऐ
    0.42
     trials
    0.41
     kesehatan
    0.40
     enfermedades
    0.40
     pengetahuan
    0.40
     timeCounter
    0.40
     actividades
    0.39
     назначения
    0.39
    POSITIVE LOGITS
    他们的
    0.41
    金属
    0.41
     revitalize
    0.39
    ̳
    0.39
    引导
    0.38
    damn
    0.38
     Anpass
    0.38
     paid
    0.37
     تخلی
    0.37
    emaakt
    0.37
    Act Density 0.001%

    No Known Activations