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

    Neuronpedia

    INDEX
    Explanations

    research funding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Css
    -0.07
     Buccane
    -0.07
    RefreshLayout
    -0.06
    Lean
    -0.06
    Facade
    -0.06
    VERBOSE
    -0.06
    todos
    -0.06
    -enabled
    -0.06
     боли
    -0.06
    Mountain
    -0.06
    POSITIVE LOGITS
    シリーズ
    0.07
     인간
    0.07
    賞
    0.06
     Monthly
    0.06
    Guest
    0.06
    :num
    0.06
    �습니다
    0.06
     Проф
    0.06
     wishlist
    0.06
    _is
    0.06
    Act Density 0.026%

    No Known Activations