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

    Neuronpedia

    INDEX
    Explanations

    code and web pages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     đẳng
    -0.07
     görd
    -0.07
    peed
    -0.07
    navigation
    -0.07
     gauss
    -0.07
    目前国内
    -0.07
    扂
    -0.07
     Latino
    -0.07
    OLS
    -0.07
    两大
    -0.07
    POSITIVE LOGITS
    小狗
    0.07
    _hide
    0.07
    =forms
    0.06
    与众不同
    0.06
     Dol
    0.06
    ="../
    0.06
    套路
    0.06
    类似于
    0.06
    [Boolean
    0.06
    //!↵
    0.06
    Act Density 0.000%

    No Known Activations