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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inaug
    -0.07
     sustaining
    -0.07
    ado
    -0.07
     libertine
    -0.07
     mosquito
    -0.07
     traditional
    -0.07
    expiration
    -0.07
    عنوان
    -0.06
    ้าอ
    -0.06
     Gaga
    -0.06
    POSITIVE LOGITS
    امت
    0.06
    */),
    0.06
    ？
    0.06
    된
    0.06
     razor
    0.06
    }));↵
    0.06
    .setColor
    0.05
               ↵
    0.05
    κό
    0.05
    _Test
    0.05
    Act Density 0.008%

    No Known Activations