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

    Neuronpedia

    INDEX
    Explanations

    either or

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    собенно
    0.64
     न्यूज़
    0.62
     conclusively
    0.61
    ңуз
    0.61
     особенно
    0.61
    opuerto
    0.60
    类别
    0.60
     अल्फा
    0.59
    ђено
    0.59
    Salut
    0.59
    POSITIVE LOGITS
     Either
    0.59
     do
    0.59
     priv
    0.58
     Zustimmung
    0.58
     p
    0.57
     j
    0.57
     share
    0.57
     reject
    0.56
     J
    0.55
     referendum
    0.55
    Act Density 0.000%

    No Known Activations