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

    Neuronpedia

    INDEX
    Explanations

    Exceptional demons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     შესაძ
    0.52
     kritis
    0.52
     noses
    0.50
     موج
    0.48
    explored
    0.48
     awakened
    0.47
     Гульнявыя
    0.46
    ⵍ
    0.45
     airs
    0.45
     दीर्घ
    0.45
    POSITIVE LOGITS
    LayoutParams
    0.50
    STER
    0.46
    Ov
    0.45
    Protection
    0.45
     sevgili
    0.45
    Nearby
    0.44
    দিন
    0.42
    情報
    0.42
    যানী
    0.42
     tess
    0.42
    Act Density 0.000%

    No Known Activations