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

    Neuronpedia

    INDEX
    Explanations

    bright

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     officer
    -0.07
     trava
    -0.07
    esimal
    -0.07
     görül
    -0.07
     Squadron
    -0.07
    #######↵
    -0.06
     effortlessly
    -0.06
    	templateUrl
    -0.06
     foss
    -0.06
     veteran
    -0.06
    POSITIVE LOGITS
     Bright
    0.09
    Bright
    0.09
     brighter
    0.08
     bright
    0.08
     outcry
    0.07
    	light
    0.07
    {EIF
    0.07
    rowth
    0.06
    (net
    0.06
     광
    0.06
    Act Density 0.009%

    No Known Activations