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

    Neuronpedia

    INDEX
    Explanations

    Index variables in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SACTION
    -0.08
    Insurance
    -0.07
    /my
    -0.07
    <boost
    -0.07
    _loaded
    -0.07
    _bytes
    -0.07
     ViewGroup
    -0.07
    container
    -0.06
     Bootstrap
    -0.06
    .subscription
    -0.06
    POSITIVE LOGITS
    讓他
    0.07
     đoạn
    0.07
    |{↵
    0.07
    '])↵
    0.07
     Hawth
    0.07
    独一
    0.06
    独一无
    0.06
    甚至连
    0.06
     Depot
    0.06
     lead
    0.06
    Act Density 0.012%

    No Known Activations