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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     racines
    -0.55
     Waterways
    -0.52
     législ
    -0.49
     traités
    -0.49
    udsman
    -0.47
     zove
    -0.46
     tű
    -0.46
     Recorder
    -0.45
     realistas
    -0.45
     évent
    -0.45
    POSITIVE LOGITS
    parsedMessage
    0.68
    StructEnd
    0.67
    <bos>
    0.61
     eds
    0.58
     HttpNotFound
    0.57
    +:+
    0.57
    __':
    0.57
     led
    0.54
     فريبيس
    0.54
     hopping
    0.54
    Act Density 0.001%

    No Known Activations