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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     závě
    -0.07
    وي
    -0.07
     cerco
    -0.07
     comenz
    -0.06
     цель
    -0.06
     alc
    -0.06
    -stack
    -0.06
    ٤
    -0.06
    IBM
    -0.06
    ١
    -0.06
    POSITIVE LOGITS
     Reader
    0.06
    퇴
    0.06
    呢
    0.06
     Lindsey
    0.06
     utilize
    0.06
     assets
    0.06
    니다
    0.06
    _cond
    0.06
     Sounds
    0.06
    ░
    0.06
    Act Density 0.000%

    No Known Activations