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

    Neuronpedia

    INDEX
    Explanations

    Russian concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ውስጥ
    0.90
    ٍ
    0.89
    നിക്ക്
    0.89
    женности
    0.85
    に
    0.85
    жному
    0.85
    <start_of_image>
    0.85
    жке
    0.84
    에는
    0.84
    اءِ
    0.83
    POSITIVE LOGITS
    으로
    1.50
    로
    1.48
     by
    1.47
    리로
    1.45
    지로
    1.43
    жением
    1.40
     등으로
    1.39
    шением
    1.37
    телями
    1.35
    выми
    1.34
    Act Density 0.020%

    No Known Activations