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

    Neuronpedia

    INDEX
    Explanations

    bounded, limited, discrete

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ि
    1.84
    ный
    1.65
    ם
    1.55
    дин
    1.51
    ㇂
    1.49
    ного
    1.48
    ке
    1.48
    すすめ
    1.47
    дать
    1.47
     overboard
    1.45
    POSITIVE LOGITS
    gens
    1.62
    ein
    1.60
    ar
    1.58
    eas
    1.49
     размеры
    1.49
    cps
    1.48
    zę
    1.46
     électronique
    1.46
    bruk
    1.46
    v
    1.44
    Act Density 0.354%

    No Known Activations