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

    Neuronpedia

    INDEX
    Explanations

    batch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Royal
    -0.07
    udev
    -0.07
    olkien
    -0.07
     "...
    -0.07
    君
    -0.07
    _video
    -0.06
    _pixels
    -0.06
    UL
    -0.06
    数组
    -0.06
    upiter
    -0.06
    POSITIVE LOGITS
     batch
    0.11
     Batch
    0.08
    atch
    0.08
    .Batch
    0.07
     batches
    0.07
     Vintage
    0.07
    批
    0.07
    .batch
    0.07
     {:?}",
    0.07
    0.06
    Act Density 0.006%

    No Known Activations