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

    Neuronpedia

    INDEX
    Explanations

    measuring time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    你会发现
    -0.07
    委员会
    -0.07
    显示器
    -0.07
     Anim
    -0.07
    晪
    -0.07
     tb
    -0.06
    igli
    -0.06
     bl
    -0.06
    一点点
    -0.06
    曦
    -0.06
    POSITIVE LOGITS
    _processed
    0.08
    _HASH
    0.07
    _TOPIC
    0.07
    FOR
    0.07
    reek
    0.06
    穄
    0.06
    ቅ
    0.06
    ipa
    0.06
    ATIONS
    0.06
    	log
    0.06
    Act Density 0.013%

    No Known Activations