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

    Neuronpedia

    INDEX
    Explanations

    positive quality descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     denominada
    0.45
     chiamato
    0.44
    এবার
    0.43
    여기
    0.42
    部長
    0.40
    NUMBER
    0.39
     presiding
    0.39
     denominado
    0.38
     called
    0.38
     xhrObj
    0.38
    POSITIVE LOGITS
    ing
    0.51
    á
    0.44
    ie
    0.42
    ía
    0.42
    ная
    0.42
    е
    0.39
    w
    0.39
    alı
    0.38
    ası
    0.38
    ā
    0.37
    Act Density 0.002%

    No Known Activations