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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	rv
    -0.07
    翡翠
    -0.07
    _nv
    -0.07
    踒
    -0.07
    úde
    -0.07
    ᶆ
    -0.07
    大爷
    -0.07
     henüz
    -0.07
    ϋ
    -0.07
    鄣
    -0.07
    POSITIVE LOGITS
    Allowed
    0.07
     """↵
    0.07
    ------------
    0.07
     Ryan
    0.07
     existing
    0.07
    (colors
    0.07
    		
↵
    0.07
     """
↵
    0.07
    主管部门
    0.07
     {
↵
    0.06
    Act Density 0.007%

    No Known Activations