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

    Neuronpedia

    INDEX
    Explanations

    Note

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hx
    -0.07
    ellow
    -0.07
     Ald
    -0.06
     padx
    -0.06
    (utils
    -0.06
    swagger
    -0.06
    .Hosting
    -0.06
    Associ
    -0.06
    /th
    -0.06
    _encoder
    -0.06
    POSITIVE LOGITS
     стала
    0.08
     не
    0.07
    ignal
    0.06
     člověk
    0.06
    bell
    0.06
    _dark
    0.06
     испыт
    0.06
    ��取
    0.06
     conson
    0.06
    ]()
    0.06
    Act Density 0.012%

    No Known Activations