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

    Neuronpedia

    INDEX
    Explanations

    General english text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cháze
    -0.07
     gentleman
    -0.06
    	ctx
    -0.06
    iễn
    -0.06
     jednoduch
    -0.06
     нею
    -0.06
     처
    -0.06
     doubted
    -0.06
    _estimators
    -0.06
    865
    -0.06
    POSITIVE LOGITS
     보호
    0.06
     versión
    0.06
    (Position
    0.06
     offenders
    0.06
     Listings
    0.06
    -delay
    0.06
    _cover
    0.06
     warning
    0.06
     endeavor
    0.06
    _IGNORE
    0.06
    Act Density 0.175%

    No Known Activations