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

    Neuronpedia

    INDEX
    Explanations

    code snippets and XML or HTML-like structures

    oai_token-act-pair · gemini-2.0-flash

    program code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HtmlAttribute
    -0.69
    IUrlHelper
    -0.63
     RSSSF
    -0.60
    OLIS
    -0.60
     Shakspeare
    -0.59
     Monark
    -0.56
     Hift
    -0.54
    anggil
    -0.54
     masculina
    -0.53
     polygons
    -0.53
    POSITIVE LOGITS
     turned
    0.52
    voit
    0.50
     turn
    0.49
    ocer
    0.49
    الحياه
    0.48
    DoubleQuotes
    0.47
     global
    0.46
    textTheme
    0.46
    KURZBESCHREIBUNG
    0.45
     consig
    0.45
    Act Density 1.274%

    No Known Activations