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

    Neuronpedia

    INDEX
    Explanations

    employment history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FAIL
    -0.06
     Emmanuel
    -0.06
     کنیم
    -0.06
     CBC
    -0.06
    월부터
    -0.06
     ceil
    -0.06
     Metric
    -0.06
    aker
    -0.06
     Ebook
    -0.06
     prostituerade
    -0.06
    POSITIVE LOGITS
     arquivo
    0.06
    ेग
    0.06
     актив
    0.06
     binnen
    0.06
     byt
    0.06
    Parameters
    0.06
    =logging
    0.06
    下的
    0.06
    \system
    0.06
     रहत
    0.06
    Act Density 0.018%

    No Known Activations