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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -show
    -0.06
     resembles
    -0.06
     electronic
    -0.06
    January
    -0.06
     fle
    -0.06
    ({},
    -0.06
    ивання
    -0.06
     Thousands
    -0.06
     neckline
    -0.06
     landscaping
    -0.06
    POSITIVE LOGITS
     flagship
    0.06
     преп
    0.06
    arduino
    0.06
     �
    0.06
    _ec
    0.06
     美
    0.06
    FORMATION
    0.06
     GitHub
    0.06
    ubble
    0.06
     targetType
    0.06
    Act Density 0.019%

    No Known Activations