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

    Neuronpedia

    INDEX
    Explanations

    em dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,
    -0.78
    -
    -0.73
    ー
    -0.65
    .
    -0.64
    1
    -0.63
    _
    -0.62
    2
    -0.61
     
    -0.60
    0
    -0.59
    t
    -0.58
    POSITIVE LOGITS
     MainAxisSize
    1.27
     Мексичка
    1.27
     виправивши
    1.27
    AddTagHelper
    1.18
    Hentet
    1.16
    ]")]
    1.14
     المعيارى
    1.12
    SourceChecksum
    1.11
     initComponents
    1.09
     дописавши
    1.09
    Act Density 0.202%

    No Known Activations