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

    Neuronpedia

    INDEX
    Explanations

    book characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ウェ
    -0.07
    	table
    -0.06
    ального
    -0.06
     comedian
    -0.06
    iky
    -0.06
     ягод
    -0.06
     McK
    -0.06
    peace
    -0.06
    _CAT
    -0.06
     شده
    -0.06
    POSITIVE LOGITS
    atcher
    0.07
     creation
    0.06
     overlay
    0.06
    ايا
    0.06
    (center
    0.06
    Palette
    0.06
     register
    0.06
     Tra
    0.06
    classification
    0.06
    ौज
    0.06
    Act Density 0.043%

    No Known Activations