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

    Neuronpedia

    INDEX
    Explanations

    Biographies/Dates of Birth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.69
     IBOutlet
    -0.69
    Geplaatst
    -0.68
     EconPapers
    -0.68
     leçons
    -0.66
    Autoritní
    -0.66
     pleaſure
    -0.65
    ^(@)
    -0.64
    TagMode
    -0.63
     Anſ
    -0.63
    POSITIVE LOGITS
    e
    0.54
    a
    0.48
    1
    0.48
    .
    0.47
     חיצוניים
    0.46
    g
    0.45
    cate
    0.45
    0.44
     above
    0.44
     would
    0.44
    Act Density 0.001%

    No Known Activations