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

    Neuronpedia

    INDEX
    Explanations

    DFS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myocard
    -0.07
    986
    -0.06
    ä
    -0.06
    itrust
    -0.06
     kisses
    -0.06
    bservable
    -0.06
    Gün
    -0.06
    	unset
    -0.06
    ivatel
    -0.06
    ;';↵
    -0.06
    POSITIVE LOGITS
    도
    0.08
     período
    0.07
     Alf
    0.06
     Dodd
    0.06
     Ard
    0.06
    ردد
    0.06
     mdl
    0.06
     Profiles
    0.06
     honoured
    0.06
     Urb
    0.06
    Act Density 0.001%

    No Known Activations