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
    _);↵
    -0.06
    谈
    -0.06
        ↵    ↵    ↵    ↵
    -0.06
    ule
    -0.06
     Sơn
    -0.06
     okamž
    -0.06
    esini
    -0.06
    -0.06
    스티
    -0.06
     estable
    -0.06
    POSITIVE LOGITS
    pad
    0.07
    сии
    0.07
    IFY
    0.07
    ности
    0.07
    caffe
    0.07
     тяж
    0.07
     безопас
    0.07
    �
    0.06
     toc
    0.06
    ате
    0.06
    Act Density 0.000%

    No Known Activations