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

    Neuronpedia

    INDEX
    Explanations

    news coverage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sanders
    -0.07
    Sanders
    -0.06
    ovní
    -0.06
    abant
    -0.06
    排
    -0.06
     entails
    -0.06
    adní
    -0.06
    ussels
    -0.06
     virgin
    -0.06
     Grammar
    -0.06
    POSITIVE LOGITS
     Streams
    0.07
     район
    0.07
        
    0.06
     防
    0.06
    ozilla
    0.06
    0.06
    Про
    0.06
    _addr
    0.06
    margin
    0.06
    тый
    0.06
    Act Density 0.019%
    No Known Activations