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

    Neuronpedia

    INDEX
    Explanations

    ML

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .FirstName
    -0.06
     �
    -0.06
    hotmail
    -0.06
    ları
    -0.06
    Technical
    -0.06
    court
    -0.06
     Calder
    -0.06
     Pars
    -0.06
     far
    -0.06
    open
    -0.06
    POSITIVE LOGITS
    (text
    0.07
    [root
    0.07
     실제
    0.07
     домов
    0.06
    تب
    0.06
     متن
    0.06
    )↵↵
    0.06
    {(
    0.06
    /{$
    0.06
     ```
    0.06
    Act Density 0.001%

    No Known Activations