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

    Neuronpedia

    INDEX
    Explanations

    articles/prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    唯一
    -0.07
    оци
    -0.07
     UR
    -0.07
    لمه
    -0.06
     this
    -0.06
    енні
    -0.06
    uttle
    -0.06
    .”↵↵
    -0.06
    言って
    -0.06
    шим
    -0.06
    POSITIVE LOGITS
    _AUD
    0.07
    본
    0.06
    eşit
    0.06
     postcode
    0.06
    .setPrototypeOf
    0.06
    lop
    0.06
    (piece
    0.06
    atile
    0.06
    _story
    0.06
    [start
    0.06
    Act Density 0.120%

    No Known Activations