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

    Neuronpedia

    INDEX
    Explanations

    legal and government related text.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Spanish
    -1.36
     Mexican
    -1.25
     Spaniard
    -1.22
    Spanish
    -1.20
     spanish
    -1.16
     Portuguese
    -1.14
     Hispanic
    -1.14
     Latino
    -1.13
     Spaniards
    -1.13
     mexican
    -1.13
    POSITIVE LOGITS
     Púb
    0.54
    expandindo
    0.52
     estekak
    0.50
     Jurí
    0.45
    ToScroll
    0.42
     Económica
    0.40
     ancianos
    0.39
     Sociales
    0.39
    ứt
    0.36
     sentencia
    0.35
    Act Density 1.221%

    No Known Activations