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

    Neuronpedia

    INDEX
    Explanations

    linguistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Drinking
    -0.09
     homeschooling
    -0.09
    -ẹrọ
    -0.08
     participa
    -0.08
     participaron
    -0.08
    EPA
    -0.08
     erwerben
    -0.08
     breastfeeding
    -0.08
     tətbi
    -0.08
    عتها
    -0.07
    POSITIVE LOGITS
     kel
    0.07
     arr
    0.07
     half
    0.07
     Fontaine
    0.07
     fluxo
    0.07
     fractured
    0.07
     colossal
    0.07
    _DIRECTION
    0.07
     magnific
    0.07
     prior
    0.07
    Act Density 0.004%

    No Known Activations