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

    Neuronpedia

    INDEX
    Explanations

    ET

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     did
    -0.07
     Matt
    -0.07
     sanctions
    -0.07
     аналог
    -0.07
    續
    -0.07
    inidad
    -0.06
    후
    -0.06
    ս
    -0.06
    吞噬
    -0.06
     dịch
    -0.06
    POSITIVE LOGITS
    _nan
    0.08
     KeyError
    0.08
     incapable
    0.07
    dragon
    0.07
    درك
    0.07
    	J
    0.07
     holy
    0.07
    semi
    0.07
    hydrate
    0.07
    _half
    0.07
    Act Density 0.002%

    No Known Activations