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

    Neuronpedia

    INDEX
    Explanations

    Ac

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    棚
    -0.07
    Cloud
    -0.07
     Cloud
    -0.06
     scout
    -0.06
    teenth
    -0.06
     PATCH
    -0.06
    enin
    -0.06
    θος
    -0.06
    eenth
    -0.06
    ่วง
    -0.06
    POSITIVE LOGITS
     каль
    0.07
    ิศ
    0.06
     ακ
    0.06
     roommate
    0.06
    ardır
    0.06
    اخر
    0.06
     ostat
    0.06
    ्रद
    0.06
    πί
    0.06
    OfMonth
    0.06
    Act Density 0.006%

    No Known Activations