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

    Neuronpedia

    INDEX
    Explanations

    mathematical functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vegan
    -0.08
    한국
    -0.08
     한국
    -0.08
     mellitus
    -0.07
    ignee
    -0.07
    _rece
    -0.07
     receipt
    -0.07
     הכנסת
    -0.07
     Reino
    -0.07
     urlencode
    -0.07
    POSITIVE LOGITS
     relied
    0.09
     recursively
    0.08
     inaccessible
    0.08
     außerhalb
    0.08
    'em
    0.07
    bitrary
    0.07
     demanded
    0.07
     unbedingt
    0.07
    (extension
    0.07
     පු
    0.07
    Act Density 0.023%

    No Known Activations