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

    Neuronpedia

    INDEX
    Explanations

    quotes from news

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incor
    -0.07
    igli
    -0.06
    ullan
    -0.06
     FUN
    -0.06
    Taken
    -0.06
     detail
    -0.06
    سان
    -0.06
     souls
    -0.06
     beh
    -0.06
    752
    -0.05
    POSITIVE LOGITS
    ยวข
    0.07
    ).
    0.07
    logger
    0.07
    cej
    0.06
     вищ
    0.06
    (mi
    0.06
    permanent
    0.06
    >).
    0.06
    _person
    0.06
    _gene
    0.06
    Act Density 0.001%

    No Known Activations