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

    Neuronpedia

    INDEX
    Explanations

    percent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    アニメ
    -0.07
    Congress
    -0.07
    ORS
    -0.07
     düş
    -0.06
    엤
    -0.06
     Ras
    -0.06
    dateFormat
    -0.06
    꿱
    -0.06
    Pages
    -0.06
    激素
    -0.06
    POSITIVE LOGITS
     multiplied
    0.07
    ;
↵
↵
↵
↵
    0.07
     mutually
    0.07
    erno
    0.07
     concentrates
    0.07
     отлично
    0.07
    찬
    0.07
    venth
    0.07
    (DateTime
    0.07
    Lv
    0.07
    Act Density 0.040%

    No Known Activations