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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    clude
    -0.06
     diese
    -0.06
     bored
    -0.06
     مشاركة
    -0.06
     механіз
    -0.06
     olası
    -0.06
    舒
    -0.06
     vừa
    -0.06
     LOL
    -0.05
    开放
    -0.05
    POSITIVE LOGITS
    егодня
    0.07
    .nextLine
    0.07
     investigate
    0.07
    .IO
    0.06
    (ptr
    0.06
     WHERE
    0.06
    VK
    0.06
     Content
    0.06
     identifier
    0.06
    criminal
    0.06
    Act Density 0.016%

    No Known Activations