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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .make
    -0.07
     Mexico
    -0.07
     Ticket
    -0.07
    display
    -0.07
    Commit
    -0.07
    refresh
    -0.06
     toilets
    -0.06
    cam
    -0.06
    tr
    -0.06
    olson
    -0.06
    POSITIVE LOGITS
     فال
    0.07
    abez
    0.06
     fino
    0.06
     Ank
    0.06
    ��
    0.06
     нерв
    0.06
    ้งาน
    0.06
     фактор
    0.06
     preocup
    0.06
     Bhar
    0.06
    Act Density 0.001%

    No Known Activations