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

    Neuronpedia

    INDEX
    Explanations

    animal killing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     agency
    -0.07
    존
    -0.06
    【
    -0.06
     depart
    -0.06
     provision
    -0.06
    وير
    -0.06
    ворення
    -0.06
    ẫu
    -0.06
    .solution
    -0.06
     traceback
    -0.06
    POSITIVE LOGITS
    銀
    0.06
     Ware
    0.06
     hacen
    0.06
    onents
    0.06
    Tasks
    0.06
    _CHARS
    0.06
    xico
    0.06
     Fireplace
    0.06
     �
    0.06
     Pacers
    0.06
    Act Density 0.137%

    No Known Activations