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

    Neuronpedia

    INDEX
    Explanations

    quotes in articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spices
    -0.07
    /boot
    -0.07
     kod
    -0.06
     진
    -0.06
    ecal
    -0.06
     당신
    -0.06
     Tout
    -0.06
     sushi
    -0.06
     frustration
    -0.06
     praising
    -0.06
    POSITIVE LOGITS
     zaměstn
    0.07
     отв
    0.07
     cleanup
    0.07
    кової
    0.06
    -prepend
    0.06
    ceived
    0.06
    _views
    0.06
     whistleblower
    0.06
    NullException
    0.06
    _finished
    0.06
    Act Density 0.073%

    No Known Activations