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

    Neuronpedia

    INDEX
    Explanations

    URLs and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    liers
    -0.07
     lệ
    -0.06
    ^[
    -0.06
     messages
    -0.06
    ｡
    -0.06
    Device
    -0.06
    ними
    -0.06
     واح
    -0.06
    下的
    -0.06
     Hastings
    -0.06
    POSITIVE LOGITS
     anak
    0.07
     пра
    0.07
    @Service
    0.06
     URLSession
    0.06
     Bil
    0.06
    ">&#
    0.06
     historically
    0.06
    ’da
    0.06
     Bd
    0.06
     ↔
    0.06
    Act Density 0.065%

    No Known Activations