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

    Neuronpedia

    INDEX
    Explanations

    Training future experts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Book
    -0.06
     dne
    -0.06
    sj
    -0.06
    .sheet
    -0.06
    권
    -0.06
     plurality
    -0.06
    .Auth
    -0.06
    _room
    -0.06
     parental
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     especific
    0.07
     importantes
    0.07
     Πολι
    0.07
     fearless
    0.07
     bringing
    0.06
     गलत
    0.06
    \n
    0.06
    ph
    0.06
     huku
    0.06
    Để
    0.06
    Act Density 0.021%

    No Known Activations