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

    Neuronpedia

    INDEX
    Explanations

    by written

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .gson
    -0.07
    .BUTTON
    -0.07
    ActiveSheet
    -0.07
    连忙
    -0.07
    =sc
    -0.06
    Property
    -0.06
     ز
    -0.06
     commend
    -0.06
    Ͳ
    -0.06
    辩
    -0.06
    POSITIVE LOGITS
     birth
    0.07
     prohibition
    0.07
    	U
    0.06
    _qs
    0.06
    犹如
    0.06
    individual
    0.06
    	addr
    0.06
    -core
    0.06
     mastering
    0.06
    �
    0.06
    Act Density 0.002%

    No Known Activations