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

    Neuronpedia

    INDEX
    Explanations

    az

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ui
    -0.07
     muj
    -0.07
    xad
    -0.07
    ROS
    -0.07
    arma
    -0.06
    _IN
    -0.06
     Bravo
    -0.06
    籽
    -0.06
    我个人
    -0.06
     Pip
    -0.06
    POSITIVE LOGITS
    滉
    0.07
     disgusting
    0.07
    앤
    0.07
    וצאות
    0.07
     כיום
    0.07
    一顿
    0.07
    一眼
    0.07
    鸨
    0.07
    🦄
    0.07
     phó
    0.07
    Act Density 0.003%

    No Known Activations