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

    Neuronpedia

    INDEX
    Explanations

    late statements cloud true Eid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    า
    0.87
    '`
    0.73
    </b>
    0.72
    ితి
    0.72
    '}
    0.69
     junction
    0.69
     seção
    0.69
    ↵↵↵↵↵
    0.69
    у
    0.69
     Sn
    0.68
    POSITIVE LOGITS
    actif
    0.76
     அட்சய
    0.75
    irez
    0.75
    risa
    0.75
    حدیث
    0.74
     Buffet
    0.73
    𝙤
    0.73
    rifft
    0.72
     করছি
    0.71
    दोस्तों
    0.71
    Act Density 0.002%

    No Known Activations