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

    Neuronpedia

    INDEX
    Explanations

    generic words used across different fields

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’
    -0.45
    </em>
    -0.44
    edo
    -0.42
    의
    -0.42
    '
    -0.42
    <bos>
    -0.41
     chiếc
    -0.41
    瑠
    -0.40
    joh
    -0.40
    tr
    -0.40
    POSITIVE LOGITS
     autorytatywna
    1.19
    Personensuche
    1.11
    RenderAtEndOf
    1.09
     tartalomajánló
    1.05
     مشين
    1.05
     للاسماء
    1.00
    GEBURTSDATUM
    0.99
    Rhestr
    0.96
    Tikang
    0.95
    verwijspagina
    0.92
    Act Density 5.593%

    No Known Activations