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

    Neuronpedia

    INDEX
    Explanations

    cover

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    γκο
    -0.08
    硬
    -0.07
    Directed
    -0.07
     Fusion
    -0.07
    sass
    -0.07
    ウェ
    -0.07
     tub
    -0.06
    ultimate
    -0.06
    稿
    -0.06
    tty
    -0.06
    POSITIVE LOGITS
     idea
    0.06
     encompass
    0.06
    nova
    0.06
     namespaces
    0.06
     nghiên
    0.06
     передбач
    0.06
     Estados
    0.06
    ียนบ
    0.06
     acquitted
    0.06
     erad
    0.05
    Act Density 0.029%

    No Known Activations