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

    Neuronpedia

    INDEX
    Explanations

    formal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     decreased
    -0.07
     seven
    -0.07
     deaths
    -0.07
     Hüs
    -0.07
    _percent
    -0.06
     количество
    -0.06
    Craig
    -0.06
     JUST
    -0.06
    likely
    -0.06
     thiên
    -0.06
    POSITIVE LOGITS
     formal
    0.09
    Fields
    0.07
     informal
    0.07
     Formal
    0.07
    simulation
    0.07
    Memo
    0.07
     sealed
    0.07
     postage
    0.07
    (Form
    0.07
     Barber
    0.06
    Act Density 0.006%

    No Known Activations