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

    Neuronpedia

    INDEX
    Explanations

    LLM, generative AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тные
    1.00
    ти
    0.95
    тів
    0.95
    دی
    0.92
    ний
    0.91
    tı
    0.89
     andere
    0.86
    dır
    0.86
    𝚝
    0.85
    mö
    0.84
    POSITIVE LOGITS
    은
    0.92
    ١
    0.92
    이면
    0.90
    1
    0.90
    3
    0.85
     dissipated
    0.80
    GA
    0.79
    2
    0.79
    餐
    0.79
    आर
    0.78
    Act Density 0.329%

    No Known Activations