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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate measurement, comparison, or degree

    oai_token-act-pair · gemini-2.0-flash

    normal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     belong
    -0.54
     thuộc
    -0.52
     belongs
    -0.52
     belonging
    -0.46
    MENAFN
    -0.45
    memberOf
    -0.45
    belong
    -0.44
    getLogger
    -0.42
    rimônio
    -0.41
    unter
    -0.40
    POSITIVE LOGITS
    Personensuche
    0.89
     Савезне
    0.79
    InjectAttribute
    0.73
    principalTable
    0.73
    GEBURTSDATUM
    0.70
    InvalidProtocol
    0.69
    الحياه
    0.69
     ***!
    0.66
     resourceCulture
    0.65
    تقاوى
    0.65
    Act Density 1.567%

    No Known Activations