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

    Neuronpedia

    INDEX
    Explanations

    tension

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (sqrt
    -0.07
    ract
    -0.07
    ủ
    -0.07
     suggests
    -0.07
     Feature
    -0.06
    Meeting
    -0.06
     gastric
    -0.06
     sys
    -0.06
     technique
    -0.06
    _FILTER
    -0.06
    POSITIVE LOGITS
     tension
    0.07
     cầu
    0.07
    的事情
    0.06
     дов
    0.06
     تصمیم
    0.06
    객
    0.06
    .Configure
    0.06
    �
    0.06
    QN
    0.06
    ZeroWidthSpace
    0.06
    Act Density 0.001%

    No Known Activations