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

    Neuronpedia

    INDEX
    Explanations

    Fake

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    пер
    -0.07
     incons
    -0.07
    通过
    -0.07
    ,(
    -0.06
     здійс
    -0.06
    -error
    -0.06
     volatility
    -0.06
    fts
    -0.06
     leveled
    -0.06
    肃
    -0.06
    POSITIVE LOGITS
    Fake
    0.12
     Fake
    0.10
    fake
    0.08
    .fake
    0.08
    _mock
    0.08
    ake
    0.07
     Mock
    0.07
     tmp
    0.07
     Coconut
    0.07
    Dummy
    0.07
    Act Density 0.003%

    No Known Activations