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

    Neuronpedia

    INDEX
    Explanations

    scientific papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Пр
    -0.07
     Avrupa
    -0.07
    /me
    -0.06
    separator
    -0.06
     اجتماعی
    -0.06
    jerne
    -0.06
     사람
    -0.06
     Furious
    -0.06
     shepherd
    -0.06
    Fallback
    -0.06
    POSITIVE LOGITS
     …
    0.07
    ์↵
    0.07
    <!
    0.07
    实在
    0.06
    [])↵
    0.06
    REV
    0.06
     وصلات
    0.06
     Tài
    0.06
    (coeffs
    0.06
     resembling
    0.06
    Act Density 0.052%

    No Known Activations