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

    Neuronpedia

    INDEX
    Explanations

    informal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     référencement
    -0.11
    េញ
    -0.08
     Parse
    -0.07
    יף
    -0.07
     naden
    -0.07
     Route
    -0.07
     lac
    -0.07
    /m
    -0.07
    Roman
    -0.07
     unpopular
    -0.07
    POSITIVE LOGITS
    이라고
    0.09
      
    0.08
     ….
    0.08
    한다고
    0.08
    ospels
    0.08
    …,
    0.08
     medically
    0.08
     Республика
    0.08
     видел
    0.08
    _bw
    0.08
    Act Density 0.389%

    No Known Activations