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

    Neuronpedia

    INDEX
    Explanations

    quantities and measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     capacidad
    -0.07
     kter
    -0.07
    μερ
    -0.07
    (bb
    -0.06
     bốn
    -0.06
     unary
    -0.06
     unters
    -0.06
     strt
    -0.06
    xn
    -0.06
     setName
    -0.06
    POSITIVE LOGITS
     Autonomous
    0.07
     elemental
    0.06
    Intialized
    0.06
     shrine
    0.06
     alarming
    0.06
     Recent
    0.06
    JK
    0.06
    .Q
    0.06
     Extremely
    0.06
    FETCH
    0.06
    Act Density 0.006%

    No Known Activations