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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .SE
    -0.07
     borderColor
    -0.06
     TRAIN
    -0.06
    .generate
    -0.06
    ıs
    -0.06
     Π
    -0.06
     problème
    -0.06
    884
    -0.06
    .translation
    -0.06
    сор
    -0.06
    POSITIVE LOGITS
    只是
    0.07
    routeParams
    0.07
    iton
    0.07
    rgyz
    0.06
    ,user
    0.06
    (al
    0.06
    ată
    0.06
    薬
    0.06
     샤
    0.06
     recount
    0.06
    Act Density 0.029%

    No Known Activations