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

    Neuronpedia

    INDEX
    Explanations

    country names and related adjectives

    oai_token-act-pair · gemini-2.0-flash

    countries/locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     metav
    -0.72
    >--}}
    -0.64
    horabuena
    -0.60
    <bos>
    -0.58
     Tym
    -0.58
    batore
    -0.58
    esModule
    -0.53
    liceerd
    -0.51
    =$?
    -0.51
     Analyse
    -0.50
    POSITIVE LOGITS
     AssemblyCulture
    0.70
    GEBURTSDATUM
    0.57
    celotti
    0.56
    djangoproject
    0.55
    TestingModule
    0.54
     незавершена
    0.50
    iencies
    0.49
    GetResponse
    0.49
    Enllaces
    0.47
    atriz
    0.46
    Act Density 2.845%

    No Known Activations