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

    Neuronpedia

    INDEX
    Explanations

    government

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    未
    -0.07
    常用的
    -0.07
    花纹
    -0.07
    shipping
    -0.07
    .squeeze
    -0.07
    .getElementsByName
    -0.07
    可能會
    -0.07
    .Component
    -0.07
     Pens
    -0.07
    	exit
    -0.07
    POSITIVE LOGITS
    isateur
    0.07
     hostility
    0.07
     ness
    0.06
    ＿
    0.06
    收款
    0.06
    idual
    0.06
     SEQ
    0.06
     explicit
    0.06
    MULT
    0.06
    _USERNAME
    0.06
    Act Density 0.130%

    No Known Activations