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

    Neuronpedia

    INDEX
    Explanations

    initials/acronyms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    even
    -0.07
    782
    -0.07
     gods
    -0.06
    (example
    -0.06
     eve
    -0.06
     mex
    -0.06
     θέση
    -0.06
    beer
    -0.06
     små
    -0.06
     دقی
    -0.06
    POSITIVE LOGITS
     Vladimir
    0.07
     BaseEntity
    0.07
     assigning
    0.06
     Receive
    0.06
     chemicals
    0.06
    Authorized
    0.06
    lict
    0.06
    _LOWER
    0.06
     Improve
    0.06
     struggled
    0.06
    Act Density 0.109%

    No Known Activations