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

    Neuronpedia

    INDEX
    Explanations

    contract

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     푸
    -0.07
     πρέπει
    -0.07
     memor
    -0.06
    Foto
    -0.06
    Bulk
    -0.06
    яс
    -0.06
     Gö
    -0.06
     Kami
    -0.06
     intermedi
    -0.06
    imal
    -0.06
    POSITIVE LOGITS
    лять
    0.08
    AIT
    0.07
     shade
    0.07
    raz
    0.07
    очек
    0.07
    [unit
    0.07
    _san
    0.07
    наче
    0.07
    	now
    0.07
    ате
    0.07
    Act Density 0.005%

    No Known Activations