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

    Neuronpedia

    INDEX
    Explanations

    X

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .timezone
    -0.07
    464
    -0.07
    220
    -0.06
    ’t
    -0.06
    .ut
    -0.06
    يب
    -0.06
    260
    -0.06
    ูต
    -0.06
    irá
    -0.06
    ۴
    -0.06
    POSITIVE LOGITS
     /**
↵
    0.07
     ilan
    0.06
    arParams
    0.06
     diagon
    0.06
    Advertis
    0.06
    (objects
    0.06
    Hillary
    0.06
     参数
    0.06
    UITableView
    0.06
     Koch
    0.06
    Act Density 0.000%

    No Known Activations