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

    Neuronpedia

    INDEX
    Explanations

    not interrupting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tä
    0.49
     Karna
    0.47
    ት
    0.45
    icier
    0.45
    वै
    0.44
     deterrence
    0.44
    worlds
    0.44
    elem
    0.44
    Zulu
    0.43
    profen
    0.43
    POSITIVE LOGITS
     μέχρι
    0.53
     جديد
    0.50
     시작
    0.49
     алгорит
    0.49
     nouvel
    0.48
    峎
    0.47
     выход
    0.47
    hkse
    0.46
     ਕ
    0.45
     بدء
    0.45
    Act Density 0.002%

    No Known Activations