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

    Neuronpedia

    INDEX
    Explanations

    research or code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -
    -0.60
    al
    -0.53
     
    -0.52
    ation
    -0.52
    ing
    -0.51
    all
    -0.50
     be
    -0.49
     V
    -0.47
     he
    -0.45
     all
    -0.45
    POSITIVE LOGITS
    __':
    1.06
    SharedDtor
    1.00
    __":
    0.99
    migrationBuilder
    0.93
    HtmlAttribute
    0.91
    windowFixed
    0.90
     TextAppearance
    0.88
     MainAxisSize
    0.88
     <=",
    0.88
     مشين
    0.87
    Act Density 0.093%

    No Known Activations