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

    Neuronpedia

    INDEX
    Explanations

    Source

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    065
    -0.06
     Tabs
    -0.06
     Replies
    -0.06
    広
    -0.06
    реж
    -0.06
    exit
    -0.06
    ReLU
    -0.06
    ченко
    -0.06
     ______
    -0.06
    ケース
    -0.06
    POSITIVE LOGITS
     hor
    0.08
    现场
    0.07
    しても
    0.07
     drawback
    0.06
    Paginator
    0.06
     toplam
    0.06
     accredited
    0.06
    還
    0.06
    #:
    0.06
    งเป
    0.06
    Act Density 0.001%

    No Known Activations