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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    umin
    -0.07
    %),
    -0.07
    é
    -0.07
    ISTRATION
    -0.06
    oder
    -0.06
    ERA
    -0.06
    óm
    -0.06
    าว
    -0.06
    ührung
    -0.06
     shade
    -0.06
    POSITIVE LOGITS
     obsess
    0.07
    <lemma
    0.07
     정신
    0.07
    county
    0.07
     pcap
    0.06
    ştır
    0.06
    urlpatterns
    0.06
     πρά
    0.06
     conservatism
    0.06
    .addEventListener
    0.06
    Act Density 0.030%

    No Known Activations