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

    Neuronpedia

    INDEX
    Explanations

    Facebook

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     호
    -0.08
     Кам
    -0.07
     večer
    -0.06
     exemp
    -0.06
     Hardcover
    -0.06
    _dll
    -0.06
    -Clause
    -0.06
     خر
    -0.06
    학회
    -0.06
     TRAN
    -0.06
    POSITIVE LOGITS
     Fund
    0.07
    ived
    0.07
    mac
    0.07
     rage
    0.06
     los
    0.06
     progressive
    0.06
    |}↵
    0.06
     enhanced
    0.06
    shopping
    0.06
    redential
    0.06
    Act Density 0.033%

    No Known Activations