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

    Neuronpedia

    INDEX
    Explanations

    record labels and publishing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    492
    -0.07
    Non
    -0.06
    _ATTR
    -0.06
    041
    -0.06
    _epochs
    -0.06
    Indian
    -0.06
    Localized
    -0.06
     Actress
    -0.06
     Jews
    -0.06
     settles
    -0.06
    POSITIVE LOGITS
     visite
    0.07
    oğan
    0.06
    play
    0.06
     chez
    0.06
    .setLayout
    0.06
     charg
    0.06
     kullanılır
    0.06
     bizim
    0.06
    owner
    0.06
     ylabel
    0.06
    Act Density 0.037%

    No Known Activations