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

    Neuronpedia

    INDEX
    Explanations

    .execute

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    piece
    -0.07
    ederation
    -0.07
     billing
    -0.07
     eventos
    -0.07
    dirs
    -0.07
    Lewis
    -0.06
     Selector
    -0.06
    .air
    -0.06
     Billing
    -0.06
     Seat
    -0.06
    POSITIVE LOGITS
     aborted
    0.07
     completely
    0.06
     mushrooms
    0.06
    ύ
    0.06
    faf
    0.06
    هه
    0.06
     totally
    0.06
    ुव
    0.06
     (!_
    0.06
     Moms
    0.06
    Act Density 0.003%

    No Known Activations