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

    Neuronpedia

    INDEX
    Explanations

    Andrea followed by surname

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ου
    1.54
    ী
    1.47
    ü
    1.43
    кою
    1.42
    n
    1.41
    า
    1.40
    ak
    1.32
    ק
    1.30
    시
    1.25
    ์
    1.23
    POSITIVE LOGITS
    скольку
    1.17
    ,
    1.13
    $,
    1.12
     (
    1.06
    %>%
    1.02
    ification
    0.95
    ación
    0.93
    ;
    0.93
     configur
    0.91
    KeyDown
    0.87
    Act Density 0.001%

    No Known Activations