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

    Neuronpedia

    INDEX
    Explanations

    math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    গ
    -0.08
    años
    -0.08
     Side
    -0.08
    .Extensions
    -0.08
     League
    -0.08
    hlen
    -0.08
     herbs
    -0.08
    Side
    -0.08
    League
    -0.08
     Herbs
    -0.08
    POSITIVE LOGITS
     successive
    0.08
    正
    0.08
     wpis
    0.08
     contribut
    0.08
     see
    0.07
     selet
    0.07
     contributions
    0.07
     indign
    0.07
     diễn
    0.07
     чу
    0.07
    Act Density 0.009%

    No Known Activations