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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    制冷
    -0.08
    States
    -0.08
    澳大利亚
    -0.07
     isLoggedIn
    -0.07
     Americas
    -0.07
    模
    -0.07
    ajes
    -0.07
     Sight
    -0.07
    _smooth
    -0.07
     GetMessage
    -0.07
    POSITIVE LOGITS
    annie
    0.07
    选择了
    0.07
    /tiny
    0.07
     finely
    0.07
    evin
    0.07
     furnish
    0.07
     первую
    0.07
     //!
    0.07
    .putInt
    0.06
     Kem
    0.06
    Act Density 0.008%

    No Known Activations