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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     佛
    -0.07
     náz
    -0.07
     �
    -0.06
     tekrar
    -0.06
    aupt
    -0.06
     що
    -0.06
    (has
    -0.06
     factions
    -0.06
     tahmin
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    Crypto
    0.07
     Dog
    0.07
    _FRIEND
    0.06
    환경
    0.06
    duct
    0.06
    &q
    0.06
     ideal
    0.06
     sine
    0.06
    merc
    0.06
     slamming
    0.06
    Act Density 0.002%

    No Known Activations