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
     �
    -0.06
    DISABLE
    -0.06
     त
    -0.06
    Celebr
    -0.06
     banc
    -0.06
    Popover
    -0.06
    Sch
    -0.06
    	container
    -0.06
     embargo
    -0.06
    Mo
    -0.06
    POSITIVE LOGITS
    aos
    0.07
    .Abs
    0.06
    طلق
    0.06
    (B
    0.06
    ilden
    0.06
    _listing
    0.06
    /aws
    0.06
     dog
    0.06
    ysters
    0.06
    **,
    0.06
    Act Density 0.006%

    No Known Activations