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

    Neuronpedia

    INDEX
    Explanations

    literature review

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    客户
    -0.08
    imps
    -0.07
     artery
    -0.07
    LI
    -0.07
    Experience
    -0.07
    Broadcast
    -0.07
    anced
    -0.07
     bitcoin
    -0.07
    chemical
    -0.06
     Hour
    -0.06
    POSITIVE LOGITS
     není
    0.06
     오늘
    0.06
    째
    0.06
     Dram
    0.06
    tsx
    0.06
    <small
    0.06
    _emails
    0.06
     �
    0.06
     mue
    0.06
     Yönetim
    0.06
    Act Density 0.148%

    No Known Activations