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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	tmp
    -0.06
    AMI
    -0.06
     implying
    -0.06
    าม
    -0.06
     fellows
    -0.06
    ‌ش
    -0.06
    BrowserRouter
    -0.06
    ertos
    -0.06
    (items
    -0.06
    .Bunifu
    -0.06
    POSITIVE LOGITS
    衣服
    0.07
    诉
    0.07
    鞋
    0.07
    (pf
    0.06
    助
    0.06
     Christine
    0.06
    팔
    0.06
     NOTHING
    0.06
    .destroy
    0.06
     culo
    0.06
    Act Density 0.057%

    No Known Activations