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

    Neuronpedia

    INDEX
    Explanations

    Product recalls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ISTRIBUT
    -0.08
    ﻼ
    -0.08
    Nam
    -0.07
    どの
    -0.07
     Natürlich
    -0.07
     Queens
    -0.07
     kısı
    -0.06
     Lung
    -0.06
     sist
    -0.06
    もらえ
    -0.06
    POSITIVE LOGITS
    _int
    0.08
     datatype
    0.08
    onyms
    0.07
     indign
    0.07
    (common
    0.07
    +f
    0.07
     deutsch
    0.07
     <<<
    0.07
    日起
    0.07
    (convert
    0.07
    Act Density 0.014%

    No Known Activations