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

    Neuronpedia

    INDEX
    Explanations

    restaurant names or words associated with restaurants in a review

    oai_token-act-pair · gemini-2.0-flash

    Locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.78
     misa
    -0.51
     StatelessWidget
    -0.51
    enumi
    -0.49
    Faker
    -0.49
     bäst
    -0.48
     schuld
    -0.47
     boba
    -0.47
    MessageTagHelper
    -0.47
    WritableDatabase
    -0.46
    POSITIVE LOGITS
     Wicidata
    0.74
    onActivityResult
    0.56
     Union
    0.54
     Crown
    0.52
     lenker
    0.52
    zicht
    0.52
    GraphicsUnit
    0.51
    mazioni
    0.50
    getline
    0.49
    SPATH
    0.48
    Act Density 0.557%

    No Known Activations