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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gomez
    -0.07
    阿根
    -0.07
    Intensity
    -0.07
    _ELEM
    -0.07
     FAC
    -0.07
     zag
    -0.07
    =
    -0.07
     Teddy
    -0.06
    ephy
    -0.06
    거든요
    -0.06
    POSITIVE LOGITS
     multiprocessing
    0.08
    -click
    0.07
    Own
    0.07
     Là
    0.07
    迪士尼
    0.07
     цена
    0.07
    剋
    0.07
     cinema
    0.07
     retailer
    0.07
    лер
    0.07
    Act Density 0.023%

    No Known Activations