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
    、一
    -0.08
    .wordpress
    -0.07
    asyonu
    -0.06
    footer
    -0.06
    _YEAR
    -0.06
    至
    -0.06
    家庭
    -0.06
     의해
    -0.06
     (<
    -0.06
     deprecated
    -0.06
    POSITIVE LOGITS
    Exercise
    0.07
     cloth
    0.07
    uyordu
    0.06
    (lp
    0.06
    .IGNORE
    0.06
     Attacks
    0.06
    ,retain
    0.06
     rais
    0.06
    .guid
    0.06
    ourt
    0.06
    Act Density 0.184%

    No Known Activations