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

    Neuronpedia

    INDEX
    Explanations

    English

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _parameter
    -0.07
    txn
    -0.06
    628
    -0.06
     Hum
    -0.06
    Kay
    -0.06
    .menu
    -0.06
     token
    -0.06
    58
    -0.06
    Token
    -0.06
    jà
    -0.06
    POSITIVE LOGITS
     English
    0.12
     England
    0.12
    England
    0.11
    english
    0.10
    English
    0.10
     english
    0.09
     anglais
    0.09
     Portug
    0.08
    ッシュ
    0.07
     punctuation
    0.07
    Act Density 0.027%

    No Known Activations