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

    Neuronpedia

    INDEX
    Explanations

    dash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    آن
    -0.06
    }");↵↵
    -0.06
     accordingly
    -0.06
     Ваш
    -0.06
    公式
    -0.06
    getRequest
    -0.06
     yön
    -0.06
    {}'.
    -0.05
     öyle
    -0.05
     kullanıcı
    -0.05
    POSITIVE LOGITS
     Awesome
    0.07
     MPG
    0.07
    +i
    0.07
     Excellent
    0.07
     rename
    0.07
     نب
    0.07
    tags
    0.07
     zahrn
    0.06
     (~
    0.06
     expedition
    0.06
    Act Density 0.015%

    No Known Activations