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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Venture
    -0.07
     revert
    -0.07
    λλ
    -0.06
     MAD
    -0.06
    ný
    -0.06
     Constant
    -0.06
    егод
    -0.06
     dell
    -0.05
    _OPERATION
    -0.05
    keiten
    -0.05
    POSITIVE LOGITS
    이야
    0.07
     från
    0.06
    突
    0.06
    ensively
    0.06
    艺
    0.06
     Blur
    0.06
    قي
    0.06
     ادامه
    0.06
    	sort
    0.06
    ollect
    0.06
    Act Density 0.013%

    No Known Activations