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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Singleton
    -0.07
     LOC
    -0.07
    316
    -0.07
    -alt
    -0.06
    686
    -0.06
    -strip
    -0.06
    irs
    -0.06
    (final
    -0.06
     생산
    -0.06
     Hwy
    -0.06
    POSITIVE LOGITS
    daughter
    0.07
    adla
    0.07
    maması
    0.07
    кт
    0.06
    adığı
    0.06
     dedim
    0.06
    ические
    0.06
    balances
    0.06
     shove
    0.06
     />';↵
    0.06
    Act Density 0.046%

    No Known Activations