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

    Neuronpedia

    INDEX
    Explanations

    import/from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🛌
    -0.08
    ʅ
    -0.08
    ᬕ
    -0.07
    ᆰ
    -0.07
    .setTimeout
    -0.07
    isicing
    -0.07
    첸
    -0.07
    ​​
    -0.07
    𝐝
    -0.07
    笕
    -0.07
    POSITIVE LOGITS
    obook
    0.08
    Ｗ
    0.07
     __________________
    0.07
    Walking
    0.07
    .business
    0.07
    _context
    0.07
     books
    0.07
     reform
    0.07
     Beyond
    0.07
     treasure
    0.06
    Act Density 0.015%

    No Known Activations