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
     trends
    -0.07
     Supplier
    -0.07
     implementation
    -0.07
    .gender
    -0.06
     podporu
    -0.06
    adt
    -0.06
    ��
    -0.06
    Operators
    -0.06
     digits
    -0.06
     confusion
    -0.06
    POSITIVE LOGITS
     bicycle
    0.07
     additives
    0.06
     حول
    0.06
    再
    0.06
     BILL
    0.06
     Bicycle
    0.06
     friday
    0.06
     Elk
    0.06
     dinheiro
    0.06
    _checkbox
    0.06
    Act Density 0.000%

    No Known Activations