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

    Neuronpedia

    INDEX
    Explanations

    screens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æ¤į
    -0.28
    *)(
    -0.27
    SS
    -0.26
    å±¥èģĮ
    -0.26
     SS
    -0.25
     macro
    -0.25
    -life
    -0.24
    ä¸ĩæĪ·
    -0.24
    污æŁĵéĺ²æ²»
    -0.24
    åIJĪ
    -0.24
    POSITIVE LOGITS
    ä¸ŃæľŁ
    0.29
    -West
    0.28
    ä¸ĭæīĭ
    0.27
    Mid
    0.27
     resend
    0.26
    _mid
    0.25
    mise
    0.25
     вÑģего
    0.25
     pessim
    0.24
     midway
    0.24
    Act Density 0.025%

    No Known Activations