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

    Neuronpedia

    INDEX
    Explanations

    ask away

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يت
    0.82
     adults
    0.74
     home
    0.73
    me
    0.70
    ensation
    0.70
    यल
    0.68
     up
    0.67
    zie
    0.66
    𝐥
    0.66
    elle
    0.66
    POSITIVE LOGITS
     variado
    0.97
    ার্জন
    0.91
    ாலின்
    0.90
    ресень
    0.90
     Algunos
    0.88
    atás
    0.87
    UILLER
    0.87
     diversidad
    0.87
    鋈
    0.87
     paisaje
    0.86
    Act Density 0.001%

    No Known Activations