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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    binding
    -0.08
     justice
    -0.08
    开元
    -0.07
     sư
    -0.07
    $wp
    -0.07
    生态圈
    -0.07
    这就是
    -0.06
     sociedad
    -0.06
    引起了
    -0.06
    .Child
    -0.06
    POSITIVE LOGITS
     rum
    0.07
     зам
    0.07
     해당
    0.07
    _WRAPPER
    0.06
    ам
    0.06
    自卑
    0.06
     erotici
    0.06
    ()}</
    0.06
    _z
    0.06
    atic
    0.06
    Act Density 0.008%

    No Known Activations