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

    Neuronpedia

    INDEX
    Explanations

    word

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adam
    -0.07
     Xavier
    -0.06
    ers
    -0.06
     LEG
    -0.06
    _outer
    -0.06
     Roger
    -0.06
    asje
    -0.06
    šet
    -0.06
     kraje
    -0.06
    .pc
    -0.06
    POSITIVE LOGITS
     قدر
    0.07
     ontvang
    0.06
    .Term
    0.06
     choked
    0.06
     expressed
    0.06
     warmth
    0.06
      ↵↵
    0.06
     standout
    0.06
    _div
    0.06
    UEST
    0.06
    Act Density 0.002%

    No Known Activations