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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     retrieving
    -0.07
     pent
    -0.07
     recreated
    -0.07
    .disconnect
    -0.06
    чит
    -0.06
     hoe
    -0.06
    \Mail
    -0.06
    _New
    -0.06
     tightly
    -0.06
     деп
    -0.06
    POSITIVE LOGITS
    ============↵
    0.06
     tímto
    0.06
     draggable
    0.06
    /.↵
    0.06
     UX
    0.06
    ーズ
    0.06
     ẩm
    0.06
    .TestCase
    0.06
     bitmap
    0.06
    -----↵↵
    0.05
    Act Density 0.102%

    No Known Activations