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

    Neuronpedia

    INDEX
    Explanations

    places and people in Europe, sometimes including titles and organizations

    oai_token-act-pair · gemini-2.0-flash

    du

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     du
    -1.32
    du
    -1.11
     Du
    -1.09
    Du
    -1.05
     DU
    -0.98
    DU
    -0.85
     Neck
    -0.70
     neck
    -0.69
     Pal
    -0.68
    Pal
    -0.65
    POSITIVE LOGITS
    IsMutable
    0.73
     Himo
    0.62
    elemField
    0.61
    XmlType
    0.61
    pausal
    0.60
    setVerticalGroup
    0.59
    principalTable
    0.59
    Clik
    0.58
     bott
    0.57
     CURIAM
    0.56
    Act Density 8.313%

    No Known Activations