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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pecies
    -0.06
     씨
    -0.06
     lou
    -0.06
     ltd
    -0.06
     constituents
    -0.06
     Studi
    -0.06
     Hizmet
    -0.06
    就
    -0.06
     Hanna
    -0.06
    .Extension
    -0.06
    POSITIVE LOGITS
    Demon
    0.07
    nob
    0.06
     granite
    0.06
     glean
    0.06
     performer
    0.06
    _remain
    0.06
    �建
    0.06
     deciding
    0.06
     follow
    0.06
     veter
    0.06
    Act Density 0.051%

    No Known Activations