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

    Neuronpedia

    INDEX
    Explanations

    Explaining parts or acronyms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    toHave
    -0.07
    _VIDEO
    -0.06
     tahun
    -0.06
    [root
    -0.06
     officials
    -0.06
    �
    -0.06
     brit
    -0.06
    ổng
    -0.06
    さんは
    -0.06
     jr
    -0.06
    POSITIVE LOGITS
    олаг
    0.07
    του
    0.07
     Farmers
    0.07
    ны
    0.06
    pressions
    0.06
    WriteBarrier
    0.06
     ACK
    0.06
    Assertion
    0.06
     выс
    0.06
     Elephant
    0.06
    Act Density 0.068%

    No Known Activations