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

    Neuronpedia

    INDEX
    Explanations

    licensing, copyright

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Theſe
    -0.76
     lenker
    -0.68
     réfugi
    -0.67
     dévelo
    -0.64
    kloped
    -0.62
    AndEndTag
    -0.61
     fallu
    -0.60
     للاسماء
    -0.59
     protoimpl
    -0.59
    UnsafeEnabled
    -0.59
    POSITIVE LOGITS
    ritsar
    0.45
    GeneratedCode
    0.45
    ."]
    0.41
    .]
    0.39
    Здра
    0.39
    ✭✭
    0.39
    lusconi
    0.38
    Slf
    0.38
    嘆
    0.37
    float
    0.37
    Act Density 0.001%

    No Known Activations