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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    攥
    -0.08
    政协
    -0.07
    读
    -0.07
     рейтинг
    -0.07
    抖音
    -0.07
     tens
    -0.07
     swapped
    -0.06
    cycl
    -0.06
     bibli
    -0.06
    子ど
    -0.06
    POSITIVE LOGITS
    六年
    0.08
    FH
    0.07
    _addresses
    0.07
    _First
    0.07
    [param
    0.07
     astronomical
    0.07
    GetProcAddress
    0.07
     phases
    0.07
    "If
    0.06
     Scheme
    0.06
    Act Density 0.002%

    No Known Activations