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

    Neuronpedia

    INDEX
    Explanations

    apply

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ederation
    -0.06
    	return
    -0.06
    	my
    -0.06
     impeachment
    -0.06
     atlas
    -0.06
     guerr
    -0.06
    _album
    -0.06
    *z
    -0.06
    pz
    -0.06
     Hao
    -0.06
    POSITIVE LOGITS
    !";↵
    0.07
     :)
    0.06
    _Part
    0.06
     "),
    0.06
     universally
    0.06
    %'↵
    0.06
    よね
    0.06
     fireplace
    0.06
    ,"↵
    0.06
     ".",
    0.06
    Act Density 0.000%

    No Known Activations