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

    Neuronpedia

    INDEX
    Explanations

    say ending uppercase

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Word
    -0.06
    sticky
    -0.06
     DER
    -0.06
    ीग
    -0.06
     Trong
    -0.06
    ティ
    -0.06
    iveness
    -0.06
    скую
    -0.06
    occupied
    -0.06
    _wrapper
    -0.06
    POSITIVE LOGITS
     Abbey
    0.06
    aşa
    0.06
     clearer
    0.06
    ccd
    0.06
     cortex
    0.06
     liv
    0.06
     DEM
    0.06
    Exam
    0.06
     Lamar
    0.06
    865
    0.06
    Act Density 0.002%

    No Known Activations