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

    Neuronpedia

    INDEX
    Explanations

    code, markup, and mixed data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wrists
    -0.07
     crawled
    -0.06
    kul
    -0.06
    еф
    -0.06
    ोफ
    -0.06
     silly
    -0.06
    zdy
    -0.06
    =f
    -0.06
     bathrooms
    -0.06
     carved
    -0.06
    POSITIVE LOGITS
    paněl
    0.07
     los
    0.07
     Marshal
    0.07
    /Area
    0.06
    batis
    0.06
    %"↵
    0.06
    athlete
    0.06
    才能
    0.06
     jumper
    0.06
    _epochs
    0.06
    Act Density 0.000%

    No Known Activations