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

    Neuronpedia

    INDEX
    Explanations

    quality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.74
     ostavi
    -0.56
     ragioni
    -0.56
     Deutschlands
    -0.55
     onCancelled
    -0.54
     onPostExecute
    -0.49
    ArrowToggle
    -0.49
    parsedMessage
    -0.49
    stateMutability
    -0.49
    orElseThrow
    -0.48
    POSITIVE LOGITS
     assured
    0.62
    assured
    0.57
    etheless
    0.57
    righted
    0.57
     social
    0.56
    weighed
    0.52
    ough
    0.52
     religious
    0.52
     maiden
    0.52
    tested
    0.51
    Act Density 0.010%

    No Known Activations