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

    Neuronpedia

    INDEX
    Explanations

    arrangement/configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fetch
    -0.06
     melt
    -0.06
    ,↵↵
    -0.06
    epend
    -0.06
    emean
    -0.06
     clocks
    -0.06
     expérience
    -0.06
    	model
    -0.06
    ((-
    -0.06
    SSI
    -0.06
    POSITIVE LOGITS
     výši
    0.08
     disguise
    0.07
     okolí
    0.07
     admiration
    0.07
    ूच
    0.07
     UsersController
    0.07
     перший
    0.07
     bringen
    0.07
     plaintiffs
    0.06
    _configure
    0.06
    Act Density 0.305%

    No Known Activations