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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to comfort, enjoyment, and ease

    oai_token-act-pair · gemini-2.0-flash

    Positive feelings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     विश्वसनीयता
    -0.82
    ConstraintMaker
    -0.73
     estimés
    -0.61
    nesses
    -0.61
     дописавши
    -0.60
    FunctionFlags
    -0.57
    ]--;
    -0.57
     CreateTagHelper
    -0.57
    XmlAccessType
    -0.56
    uxxxx
    -0.55
    POSITIVE LOGITS
    VideoCapture
    0.61
    dymyr
    0.47
    FXMLLoader
    0.47
    <bos>
    0.45
    iecie
    0.45
    Iné
    0.44
    requestCode
    0.44
     therein
    0.43
     sibi
    0.43
    CTYPE
    0.43
    Act Density 1.416%

    No Known Activations