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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ін
    -0.06
     restrictive
    -0.06
     EPS
    -0.06
    iscard
    -0.06
    (targetEntity
    -0.06
     müş
    -0.06
    .").
    -0.06
    Associated
    -0.06
     tegen
    -0.06
     Ka
    -0.06
    POSITIVE LOGITS
    сед
    0.07
     updating
    0.06
    orm
    0.06
     spiral
    0.06
    _ue
    0.06
    trieve
    0.06
     engineers
    0.06
     Atlantic
    0.06
    -sized
    0.06
    _score
    0.06
    Act Density 0.013%

    No Known Activations