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

    Neuronpedia

    INDEX
    Explanations

    Filler words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ử
    -0.06
     inne
    -0.06
    inside
    -0.06
     PostgreSQL
    -0.06
    nj
    -0.06
    igate
    -0.06
     Excel
    -0.06
    iếp
    -0.06
     affiliation
    -0.06
    شب
    -0.06
    POSITIVE LOGITS
     reside
    0.07
    hopefully
    0.07
    bounding
    0.07
    (acc
    0.07
    _builder
    0.06
    (product
    0.06
     retrie
    0.06
    用的
    0.06
    stitute
    0.06
     jump
    0.06
    Act Density 0.158%

    No Known Activations