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

    Neuronpedia

    INDEX
    Explanations

    told

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    욱
    -0.07
    앤
    -0.06
    Cars
    -0.06
    	damage
    -0.06
    heritance
    -0.06
    LEG
    -0.06
    Theory
    -0.06
    アン
    -0.06
    leg
    -0.06
    Tit
    -0.06
    POSITIVE LOGITS
     electrical
    0.07
    [cur
    0.07
    outine
    0.06
     cross
    0.06
    _FINAL
    0.06
     displ
    0.06
     attain
    0.06
     require
    0.06
    工程
    0.06
     certs
    0.06
    Act Density 0.008%

    No Known Activations