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

    Neuronpedia

    INDEX
    Explanations

    dialogue narratives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bullet
    -0.07
     tg
    -0.07
     스트
    -0.06
    acb
    -0.06
    period
    -0.06
     UIB
    -0.06
    ocate
    -0.06
    ombo
    -0.06
    _br
    -0.06
    MAT
    -0.06
    POSITIVE LOGITS
    rame
    0.07
     Bild
    0.07
     《
    0.07
     )↵↵↵
    0.06
    унок
    0.06
    《
    0.06
     emphasized
    0.06
     인간
    0.06
    elry
    0.06
     dụng
    0.06
    Act Density 0.012%

    No Known Activations