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

    Neuronpedia

    INDEX
    Explanations

    amount of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _le
    -0.06
    haled
    -0.06
     cane
    -0.06
     vodka
    -0.06
    _statistics
    -0.06
    otional
    -0.06
    ln
    -0.06
    -plus
    -0.06
    _sw
    -0.06
    oden
    -0.06
    POSITIVE LOGITS
     افزار
    0.07
     trực
    0.07
     seventeen
    0.07
     способ
    0.07
      ↵
    0.07
    bind
    0.07
    ()));
    0.07
     tasting
    0.07
     onClose
    0.07
    홀
    0.06
    Act Density 0.019%

    No Known Activations