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

    Neuronpedia

    INDEX
    Explanations

    his

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     London's
    -0.09
     gathered
    -0.08
    Paris
    -0.08
    πη
    -0.08
     cheap
    -0.08
     erotic
    -0.08
    lys
    -0.08
     barata
    -0.08
     paris
    -0.08
     پیر
    -0.08
    POSITIVE LOGITS
     varsity
    0.15
     freshman
    0.14
     NCAA
    0.13
     sophomore
    0.12
     freshmen
    0.12
     scholarships
    0.12
     ಕಾಲೇಜ
    0.11
     collegiate
    0.11
     ವಿದ್ಯಾರ್ಥ
    0.11
     coursework
    0.11
    Act Density 0.130%

    No Known Activations