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

    Neuronpedia

    INDEX
    Explanations

    countries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Load
    -0.07
    改正
    -0.07
    ὦ
    -0.07
    Bold
    -0.07
     בדבר
    -0.07
     Holly
    -0.06
    搜狐
    -0.06
     comparator
    -0.06
    ,time
    -0.06
    _ld
    -0.06
    POSITIVE LOGITS
     ep
    0.07
    esp
    0.07
     infections
    0.07
    댔
    0.07
    -that
    0.07
     JSBracketAccess
    0.07
    ER
    0.07
    '/
    0.07
    感叹
    0.06
    geh
    0.06
    Act Density 0.112%

    No Known Activations