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

    Neuronpedia

    INDEX
    Explanations

    medial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     naprost
    -0.07
     spikes
    -0.07
    ergency
    -0.07
    λιά
    -0.07
     provinces
    -0.07
    unicode
    -0.06
     bureaucracy
    -0.06
    alertView
    -0.06
     пти
    -0.06
     stature
    -0.06
    POSITIVE LOGITS
     repl
    0.06
     مرکزی
    0.06
     ю
    0.06
     потрап
    0.06
    EG
    0.06
     observe
    0.06
     scrim
    0.06
     облад
    0.06
     роб
    0.06
     breached
    0.06
    Act Density 0.013%

    No Known Activations