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

    Neuronpedia

    INDEX
    Explanations

    News articles about crime

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imps
    -0.07
     Dat
    -0.06
    choose
    -0.06
    lil
    -0.06
    ./
    -0.06
    Spi
    -0.06
    ict
    -0.06
    _en
    -0.06
    ,!
    -0.06
     Everywhere
    -0.05
    POSITIVE LOGITS
    UIBarButtonItem
    0.07
    .Proxy
    0.06
    šov
    0.06
     Ngày
    0.06
    ponge
    0.06
    COORD
    0.06
    Roz
    0.06
    zh
    0.06
    .PL
    0.06
    tpl
    0.06
    Act Density 0.024%

    No Known Activations