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

    Neuronpedia

    INDEX
    Explanations

    saw

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     билан
    0.61
     минут
    0.61
     جميع
    0.57
     letzte
    0.57
     dunia
    0.54
     модуль
    0.53
     früheren
    0.53
     ඔවුන්
    0.52
     einfache
    0.52
     nawet
    0.52
    POSITIVE LOGITS
    closed
    0.54
    Match
    0.54
    olia
    0.49
    P
    0.49
    inisc
    0.47
    ónicos
    0.47
    pubescens
    0.46
     Specialties
    0.46
    Futures
    0.45
    oder
    0.45
    Act Density 0.001%

    No Known Activations