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

    Neuronpedia

    INDEX
    Explanations

    Champions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _AA
    -0.07
    ラック
    -0.07
     đ�
    -0.07
     blur
    -0.07
     ALT
    -0.07
    길
    -0.07
    Listeners
    -0.07
     Enlight
    -0.06
    parsers
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Champions
    0.14
    ampions
    0.08
     Champion
    0.07
     champions
    0.07
     maxHeight
    0.07
     deter
    0.07
     defective
    0.07
     centerpiece
    0.06
    Пер
    0.06
     #
↵
    0.06
    Act Density 0.001%

    No Known Activations