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

    Neuronpedia

    INDEX
    Explanations

    ],

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /dom
    -0.07
    原创
    -0.07
    为例
    -0.07
    aways
    -0.07
    xf
    -0.07
    Operating
    -0.07
    tec
    -0.07
     Fe
    -0.06
    มา
    -0.06
    敗
    -0.06
    POSITIVE LOGITS
     الدني
    0.07
    ursal
    0.07
    嶙
    0.07
    柚
    0.07
     Clim
    0.07
    鄀
    0.07
     Crud
    0.07
     buflen
    0.07
     Reeves
    0.06
     JMenuItem
    0.06
    Act Density 0.009%

    No Known Activations