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

    Neuronpedia

    INDEX
    Explanations

    .s, .t, .2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meny
    0.42
     nila
    0.39
    ↵↵
    0.39
    0.37
     королев
    0.37
     alles
    0.35
     onda
    0.34
    <0xC2>
    0.34
     T
    0.34
     экзем
    0.34
    POSITIVE LOGITS
    వెట్‌
    0.66
    кансер
    0.61
    patx
    0.61
    کروچ
    0.60
    Ī
    0.60
     llu
    0.59
    ِمض
    0.59
     kahelar
    0.59
     পধ্য
    0.59
    𒄘
    0.59
    Act Density 0.015%

    No Known Activations