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

    Neuronpedia

    INDEX
    Explanations

    seemed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ga
    -0.07
    ıl
    -0.07
    ğın
    -0.07
     hukuk
    -0.07
    buz
    -0.07
    ňují
    -0.07
     гід
    -0.07
    intestinal
    -0.06
    ğim
    -0.06
    ками
    -0.06
    POSITIVE LOGITS
    fortune
    0.06
    -owned
    0.06
     testimon
    0.06
    の子
    0.06
     MessageLookup
    0.06
    TW
    0.06
    onymous
    0.06
    completion
    0.06
    ISIBLE
    0.06
    _STREAM
    0.06
    Act Density 0.014%

    No Known Activations