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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Quarter
    -0.07
    _Search
    -0.07
    pression
    -0.07
    ania
    -0.07
     Celebrity
    -0.07
    Anywhere
    -0.07
     marketer
    -0.06
    >No
    -0.06
    erties
    -0.06
    anter
    -0.06
    POSITIVE LOGITS
    _conn
    0.07
    ाफ
    0.06
    اسات
    0.06
    ार
    0.06
    ат
    0.06
     economic
    0.06
    -prof
    0.06
     chiff
    0.06
    _return
    0.06
     数
    0.06
    Act Density 0.002%

    No Known Activations