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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ologue
    -0.07
     doprov
    -0.07
     алког
    -0.07
    .must
    -0.07
    áže
    -0.07
     مذ
    -0.07
    repos
    -0.06
     Чтобы
    -0.06
     ITS
    -0.06
    getPage
    -0.06
    POSITIVE LOGITS
    fm
    0.08
    guna
    0.06
    分
    0.06
    gen
    0.06
     Nepal
    0.06
    .ra
    0.06
     )]↵
    0.06
    allen
    0.06
    ğimiz
    0.06
     &
    0.06
    Act Density 0.031%

    No Known Activations