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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рев
    -0.48
     ''),
    -0.44
     Rate
    -0.43
    بوابة
    -0.43
    ”,
    -0.42
    Rate
    -0.41
    ”),
    -0.40
    "),
    -0.38
    ",
    -0.38
    “,
    -0.38
    POSITIVE LOGITS
     CreateTagHelper
    0.80
     hObject
    0.73
    tagHelperRunner
    0.71
     defaultstate
    0.69
    postmedia
    0.69
     EconPapers
    0.66
    BufferException
    0.65
    帖最后由
    0.63
     חיצוניים
    0.63
    styleType
    0.62
    Act Density 0.001%

    No Known Activations