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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CF
    -0.07
    _adj
    -0.07
    _std
    -0.06
    -0.06
     sanitation
    -0.06
    岩
    -0.06
    .dot
    -0.06
    	synchronized
    -0.06
     four
    -0.06
    .poster
    -0.06
    POSITIVE LOGITS
    。一
    0.07
    كرة
    0.07
     сбор
    0.07
     متن
    0.06
     Thực
    0.06
     stimulate
    0.06
                  
↵
    0.06
    ः
    0.06
     anchor
    0.06
    ิกายน
    0.06
    Act Density 0.095%

    No Known Activations