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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kara
    -0.07
    @Resource
    -0.06
    ترل
    -0.06
     /*#__
    -0.06
    Prod
    -0.06
    /down
    -0.06
     Wick
    -0.06
     nalez
    -0.06
     藤
    -0.06
    obia
    -0.06
    POSITIVE LOGITS
    PictureBox
    0.07
    風
    0.07
    .label
    0.07
    804
    0.07
    459
    0.07
     say
    0.07
     socks
    0.07
    ]):↵
    0.06
     فض
    0.06
    !$
    0.06
    Act Density 0.000%

    No Known Activations