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

    Neuronpedia

    INDEX
    Explanations

    _SOURCE

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    очные
    -0.08
    etsy
    -0.08
    ắ
    -0.08
    yc
    -0.07
    名誉
    -0.07
    nych
    -0.07
    <
    -0.07
    aty
    -0.07
     viele
    -0.07
     news
    -0.07
    POSITIVE LOGITS
    Roll
    0.08
    张某
    0.07
    ],↵
    0.07
     pressed
    0.06
    给大家
    0.06
    License
    0.06
    _REPO
    0.06
    	version
    0.06
     node
    0.06
    منظومة
    0.06
    Act Density 0.006%

    No Known Activations