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

    Neuronpedia

    INDEX
    Explanations

    metaphors for political competition, maneuvers and positions.

    oai_token-act-pair · gemini-2.0-flash

    Politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.93
    UnsafeEnabled
    -0.52
     ffilmiau
    -0.47
    Autoritní
    -0.45
    BeginContext
    -0.44
    #
    -0.43
    Litteratur
    -0.42
     Italijanski
    -0.41
    مصادر
    -0.40
    XmlAccessType
    -0.40
    POSITIVE LOGITS
     glyphicon
    0.60
    SharedCtor
    0.60
     يتيمه
    0.60
     consultato
    0.59
    ondissement
    0.57
     مشين
    0.57
    ({});
    0.57
    MENAFN
    0.56
    vedic
    0.56
    __);
    0.56
    Act Density 1.506%

    No Known Activations