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

    Neuronpedia

    INDEX
    Explanations

    array

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Recovery
    -0.08
     यी
    -0.08
     Ane
    -0.08
     outage
    -0.08
     navigating
    -0.08
    rupt
    -0.07
     flooding
    -0.07
    ruption
    -0.07
     umut
    -0.07
     ecology
    -0.07
    POSITIVE LOGITS
     electrically
    0.09
     elektrisch
    0.08
     compiled
    0.08
     reds
    0.07
    ندية
    0.07
    聲
    0.07
    	constructor
    0.07
    သား
    0.07
     dens
    0.07
    .compile
    0.07
    Act Density 0.003%

    No Known Activations