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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    馕
    -0.08
     fø
    -0.07
     logos
    -0.07
    _ARCH
    -0.07
     nhất
    -0.07
    gene
    -0.07
    　　
    -0.07
     inici
    -0.06
    $$
    -0.06
    💊
    -0.06
    POSITIVE LOGITS
    /Login
    0.08
    /bg
    0.07
    omin
    0.07
    ponsored
    0.07
    جمل
    0.07
     balloons
    0.07
    _groups
    0.07
    抽查
    0.07
     Benn
    0.07
    布莱
    0.07
    Act Density 0.002%

    No Known Activations