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

    Neuronpedia

    INDEX
    Explanations

    Amazon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cfg
    -0.07
    pdev
    -0.07
     Extraction
    -0.07
    owanie
    -0.07
     Bauer
    -0.07
    的各种
    -0.07
    su
    -0.07
    仕
    -0.07
    MR
    -0.07
     msec
    -0.07
    POSITIVE LOGITS
    ınd
    0.07
     Пос
    0.07
     repositories
    0.07
    .Unit
    0.07
    _projects
    0.07
     repository
    0.07
    ยาว
    0.07
     &___
    0.07
    𝗹
    0.07
    大片
    0.06
    Act Density 0.007%

    No Known Activations