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

    Neuronpedia

    INDEX
    Explanations

    Collusion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (":
    -0.08
     Ultimately
    -0.07
    苟
    -0.07
    Attachments
    -0.07
    Видео
    -0.07
    ":[{"
    -0.07
    [:]↵
    -0.07
     obliged
    -0.07
     الج
    -0.06
     cog
    -0.06
    POSITIVE LOGITS
    パー
    0.08
    бр
    0.08
    _AI
    0.08
     Ди
    0.07
    dux
    0.07
     לפתוח
    0.07
     Producer
    0.07
    _Price
    0.07
    设有
    0.07
    Ь
    0.07
    Act Density 0.015%

    No Known Activations