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

    Neuronpedia

    INDEX
    Explanations

    names and followed-by terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    标注
    0.42
    cador
    0.38
    蛾
    0.38
    淢
    0.37
     செய்தார்
    0.37
    decoration
    0.36
    MRS
    0.36
     दादी
    0.36
    Reserv
    0.36
     بينا
    0.36
    POSITIVE LOGITS
     Gree
    0.39
    dataReader
    0.38
    ಿದ
    0.37
     approximations
    0.36
     devolved
    0.36
    gesture
    0.35
     Suzuki
    0.35
     approximation
    0.34
     practising
    0.34
     darum
    0.34
    Act Density 0.002%

    No Known Activations