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

    Neuronpedia

    INDEX
    Explanations

    accusations and knowledge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (dispatch
    -0.06
    Sleep
    -0.06
    �
    -0.06
     Buffalo
    -0.06
    詩
    -0.06
    化学
    -0.06
    ]';↵
    -0.06
     teg
    -0.06
    cube
    -0.06
    ทำ
    -0.06
    POSITIVE LOGITS
    -specific
    0.07
    /**↵↵
    0.06
     yolc
    0.06
     inFile
    0.06
    /gr
    0.06
    ätz
    0.06
     AsyncTask
    0.06
    —and
    0.06
    中央
    0.06
     RTWF
    0.06
    Act Density 0.048%

    No Known Activations