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

    Neuronpedia

    INDEX
    Explanations

    kidding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ara
    -0.06
    mb
    -0.06
     �
    -0.06
     xét
    -0.06
     dép
    -0.06
    695
    -0.06
     trải
    -0.06
    Than
    -0.06
    _simple
    -0.06
     experiencia
    -0.06
    POSITIVE LOGITS
     ниж
    0.07
    告
    0.06
    рук
    0.06
    주시
    0.06
    监听
    0.06
    chron
    0.06
    """
    0.06
    CEF
    0.06
    Robot
    0.06
     mimic
    0.06
    Act Density 0.006%

    No Known Activations