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

    Neuronpedia

    INDEX
    Explanations

    Formal writing/articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     faulty
    -0.06
    衛
    -0.06
    .dead
    -0.06
     ई
    -0.06
    него
    -0.06
    اج
    -0.06
    [hash
    -0.06
    ество
    -0.06
     prized
    -0.06
    cls
    -0.06
    POSITIVE LOGITS
     """↵
    0.07
    toi
    0.07
    ();}↵
    0.07
     bulunmaktadır
    0.06
    ++];↵
    0.06
    .Constants
    0.06
     """
↵
↵
    0.06
     Lightweight
    0.06
     }*/↵
    0.06
    }";↵↵
    0.06
    Act Density 0.000%

    No Known Activations