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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Some
    -0.06
    .oauth
    -0.06
    е�
    -0.06
    太过
    -0.06
    珞
    -0.06
     الحديد
    -0.06
    lessness
    -0.06
    /Admin
    -0.06
    -0.06
    }s
    -0.06
    POSITIVE LOGITS
    _impl
    0.07
    逐
    0.07
     brewed
    0.07
    相机
    0.07
    ycling
    0.07
    Յ
    0.07
     بل
    0.07
    _EMIT
    0.06
    씼
    0.06
    规避
    0.06
    Act Density 0.374%

    No Known Activations