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

    Neuronpedia

    INDEX
    Explanations

    medical errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     přist
    -0.07
    _dist
    -0.07
     연결
    -0.07
    、この
    -0.07
    -range
    -0.06
    anko
    -0.06
    (food
    -0.06
    После
    -0.06
    (Utils
    -0.06
     Watkins
    -0.06
    POSITIVE LOGITS
     Consum
    0.07
    _photos
    0.07
     overwhelmingly
    0.07
    .GetInstance
    0.06
    .Directory
    0.06
    icemail
    0.06
     BREAK
    0.06
    agher
    0.06
     Goblin
    0.06
    較
    0.06
    Act Density 0.082%

    No Known Activations