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

    Neuronpedia

    INDEX
    Explanations

    command line help messages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intimacy
    -0.08
     বহ
    -0.07
     beneath
    -0.07
     fór
    -0.07
     لديها
    -0.07
    业
    -0.07
     organic
    -0.07
     stitched
    -0.07
     llegada
    -0.07
     cohesive
    -0.07
    POSITIVE LOGITS
    /help
    0.10
    退出
    0.09
     옵션
    0.09
    _help
    0.09
    /version
    0.09
     optie
    0.09
     getopt
    0.09
     도움
    0.09
    查看
    0.09
     режим
    0.08
    Act Density 0.004%

    No Known Activations