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

    Neuronpedia

    INDEX
    Explanations

    URLs to news articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jesse
    -0.07
    砠
    -0.07
     credits
    -0.07
    constructed
    -0.07
    ирования
    -0.07
    iedade
    -0.07
    зык
    -0.07
    يمة
    -0.07
    ille
    -0.07
    限定
    -0.06
    POSITIVE LOGITS
    Т
    0.07
     disput
    0.07
    Alarm
    0.06
     flavors
    0.06
     pistols
    0.06
    _REG
    0.06
    _players
    0.06
    股份
    0.06
    _uart
    0.06
    	opt
    0.06
    Act Density 0.015%

    No Known Activations