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
    Localization
    -0.07
    lug
    -0.07
    akens
    -0.07
    ListView
    -0.07
     KP
    -0.07
    加分
    -0.07
     flatten
    -0.06
     wrestlers
    -0.06
    相互
    -0.06
    ద
    -0.06
    POSITIVE LOGITS
    abal
    0.07
    `
↵
    0.07
     });
↵
    0.07
    =-=-=-=-
    0.06
    yx
    0.06
     الفور
    0.06
    ``
    0.06
    `↵↵
    0.06
    �
    0.06
    了吗
    0.06
    Act Density 0.024%

    No Known Activations