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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Letters
    -0.06
    Pok
    -0.06
    Something
    -0.06
     something
    -0.06
     مسئله
    -0.06
     nominate
    -0.06
    (writer
    -0.06
     rustic
    -0.06
    Power
    -0.06
     realtime
    -0.06
    POSITIVE LOGITS
     atm
    0.07
    :YES
    0.07
     无
    0.07
    emailer
    0.07
    _CAN
    0.07
     thủy
    0.06
    .’”↵↵
    0.06
    	suite
    0.06
    .paint
    0.06
    	cin
    0.06
    Act Density 0.002%

    No Known Activations