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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NIL
    -0.08
     Mul
    -0.07
     kval
    -0.07
    аті
    -0.06
    .po
    -0.06
    Sql
    -0.06
    ��
    -0.06
    �
    -0.06
     película
    -0.06
    儀
    -0.06
    POSITIVE LOGITS
     presentations
    0.07
     EventBus
    0.06
     (![
    0.06
    _rule
    0.06
    (月
    0.06
     subsidies
    0.06
     dorm
    0.06
     salmon
    0.06
     Saturday
    0.06
    uch
    0.06
    Act Density 0.000%

    No Known Activations