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

    Neuronpedia

    INDEX
    Explanations

    command line interfaces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]=(
    -0.08
    abb
    -0.08
    注册
    -0.07
    _this
    -0.07
     جن
    -0.07
    命
    -0.06
     Zak
    -0.06
     maths
    -0.06
    รก
    -0.06
     medals
    -0.06
    POSITIVE LOGITS
     Natur
    0.07
     citation
    0.06
     platform
    0.06
     Brewers
    0.06
     Termin
    0.06
     Argument
    0.06
     GROUP
    0.06
    WARNING
    0.06
     wxString
    0.06
    asctime
    0.06
    Act Density 0.027%

    No Known Activations