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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ordered
    -0.07
     flattering
    -0.07
     DIY
    -0.07
     육
    -0.07
    ariate
    -0.06
     finan
    -0.06
    รค
    -0.06
    ausible
    -0.06
     XII
    -0.06
    -th
    -0.06
    POSITIVE LOGITS
     :
    0.07
     قبل
    0.06
    :-
    0.06
     Now
    0.06
    oned
    0.06
     invis
    0.06
    %↵↵
    0.06
    nant
    0.06
    img
    0.06
     NotImplemented
    0.06
    Act Density 0.003%

    No Known Activations