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

    Neuronpedia

    INDEX
    Explanations

    no followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    k
    1.45
    ől
    1.43
    kende
    1.41
    kannya
    1.35
    ierrez
    1.33
    ming
    1.28
     入り
    1.28
    kör
    1.27
    pra
    1.24
    to
    1.23
    POSITIVE LOGITS
     불구하고
    1.73
    ور
    1.52
    ઁ
    1.44
    一丝
    1.41
     entanto
    1.39
    ва
    1.32
     obstante
    1.24
    ผู้
    1.18
     demás
    1.18
    르
    1.18
    Act Density 0.055%

    No Known Activations