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

    Neuronpedia

    INDEX
    Explanations

    variety of text types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .
    -0.68
    ).
    -0.63
    ++.
    -0.55
    ↵
    -0.50
    。
    -0.49
    ".
    -0.47
    ::
    -0.47
     ہیں۔
    -0.46
    '.
    -0.46
     much
    -0.45
    POSITIVE LOGITS
    تقاوى
    1.16
    WireFormatLite
    0.91
    Geplaatst
    0.85
    KURZBESCHREIBUNG
    0.85
    ftagPool
    0.85
    `,
    0.80
     betweenstory
    0.79
    interopRequire
    0.79
    ,
    0.72
    PreferredItem
    0.71
    Act Density 0.392%

    No Known Activations