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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lay
    -0.06
    (=)
    -0.06
    اند
    -0.06
    ayment
    -0.06
    len
    -0.06
     submits
    -0.06
    Assigned
    -0.06
     швидко
    -0.06
    DOMAIN
    -0.06
    gi
    -0.06
    POSITIVE LOGITS
     การ
    0.08
     노하우
    0.07
     Garland
    0.07
     parçası
    0.07
     Signals
    0.06
     canvas
    0.06
    IMITER
    0.06
     psychosis
    0.06
     minimise
    0.06
     TODO
    0.06
    Act Density 0.005%

    No Known Activations