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

    Neuronpedia

    INDEX
    Explanations

    tweet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alic
    -0.07
     piano
    -0.06
    aries
    -0.06
     infix
    -0.06
     scissors
    -0.06
    SR
    -0.06
     Ca
    -0.06
     Caroline
    -0.06
     Auckland
    -0.06
    dojo
    -0.06
    POSITIVE LOGITS
    tweet
    0.10
     tweet
    0.09
    _tweet
    0.08
     Tweet
    0.08
     tweeted
    0.08
    Tweet
    0.07
    tweets
    0.07
     tweeting
    0.07
     Tweets
    0.07
    mt
    0.07
    Act Density 0.004%

    No Known Activations