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

    Neuronpedia

    INDEX
    Explanations

    math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Noble
    -0.08
    -ok
    -0.06
     significa
    -0.06
    bff
    -0.06
     Drum
    -0.06
    bach
    -0.06
     assign
    -0.06
    <d
    -0.06
     worse
    -0.06
     loro
    -0.06
    POSITIVE LOGITS
    0.08
    .Annotation
    0.07
    0.07
     horizontal
    0.07
    ‌المل
    0.07
    .CODE
    0.06
     эксп
    0.06
    )↵↵↵↵
    0.06
     cái
    0.06
     nợ
    0.06
    Act Density 0.017%

    No Known Activations