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

    Neuronpedia

    INDEX
    Explanations

    article excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     :)↵↵
    -0.07
     devout
    -0.07
    _CE
    -0.07
     Durham
    -0.06
     Μον
    -0.06
    _RD
    -0.06
    Disallow
    -0.06
    xDE
    -0.06
    .xy
    -0.06
    	uint
    -0.06
    POSITIVE LOGITS
    avirus
    0.07
     NGC
    0.06
    (eval
    0.06
     과정
    0.06
     hackers
    0.06
    techn
    0.06
     tapped
    0.06
     budgets
    0.06
    angers
    0.06
     protect
    0.06
    Act Density 0.195%

    No Known Activations