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

    Neuronpedia

    INDEX
    Explanations

    historical fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	RTLI
    -0.06
    AsStream
    -0.06
     Jurassic
    -0.06
    _choose
    -0.06
    青年
    -0.06
    觉
    -0.06
     设置
    -0.06
    izada
    -0.05
     holster
    -0.05
    理
    -0.05
    POSITIVE LOGITS
     Official
    0.07
     bogus
    0.07
     Chief
    0.07
     tinha
    0.06
    ataka
    0.06
     pursuits
    0.06
     Wallet
    0.06
     RM
    0.06
    placeholder
    0.06
    NewItem
    0.06
    Act Density 0.014%

    No Known Activations