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

    Neuronpedia

    INDEX
    Explanations

    Hope and assistance requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beard
    -0.07
    _organization
    -0.07
    .nb
    -0.07
    题
    -0.06
    Cards
    -0.06
     забезпеч
    -0.06
    Effective
    -0.06
     обеспеч
    -0.06
     Rounds
    -0.06
     Texans
    -0.06
    POSITIVE LOGITS
     desper
    0.07
    126
    0.07
     junto
    0.07
    ۱۶
    0.07
    ベル
    0.06
     Další
    0.06
     Es
    0.06
    SER
    0.06
    oples
    0.06
     гор
    0.06
    Act Density 0.030%

    No Known Activations