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

    Neuronpedia

    INDEX
    Explanations

    resolve, difference, equivalence, make, mix, rooted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     স্বয়ং
    0.42
     wich
    0.37
     অবি
    0.36
     yh
    0.35
    hd
    0.35
     Luo
    0.35
    ies
    0.34
    স্‌
    0.34
    zuf
    0.33
     weib
    0.33
    POSITIVE LOGITS
    нал
    0.42
    пература
    0.42
    ч
    0.41
    ندي
    0.40
    лава
    0.39
    Фран
    0.39
    غرافيا
    0.39
    ордина
    0.39
    моль
    0.39
    Ꮞ
    0.39
    Act Density 0.076%

    No Known Activations