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

    Neuronpedia

    INDEX
    Explanations

    last closing price

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     groundwork
    0.44
    ulants
    0.41
    いく
    0.40
     corpora
    0.40
     fruct
    0.40
    unque
    0.39
     cendré
    0.39
     vieux
    0.39
     quels
    0.39
     quais
    0.38
    POSITIVE LOGITS
    ㅉ
    0.40
    鄢
    0.38
    Ꮫ
    0.38
     ');
    0.38
    рити
    0.37
    ร้อง
    0.37
    ताना
    0.37
     conformance
    0.37
    icama
    0.37
    ாட
    0.35
    Act Density 0.000%

    No Known Activations