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

    Neuronpedia

    INDEX
    Explanations

    Uncommon / foreign names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     홈페이지
    -0.07
     ERROR
    -0.07
     Inbox
    -0.07
     BOX
    -0.07
     Jobs
    -0.07
     Skills
    -0.07
    ホテル
    -0.07
    Skills
    -0.07
    getAll
    -0.07
    Exist
    -0.07
    POSITIVE LOGITS
     phương
    0.07
     Jamie
    0.07
    ऑ
    0.07
    -Americ
    0.06
     naughty
    0.06
    📃
    0.06
    rites
    0.06
     comparable
    0.06
     Mitch
    0.06
    _Mod
    0.06
    Act Density 0.277%

    No Known Activations