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

    Neuronpedia

    INDEX
    Explanations

    words that express extreme positivity or admiration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Positive superlatives

    np_acts-logits-general · gemini-2.0-flash

    words of admiration and high quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hart
    -0.53
    te
    -0.51
     hjer
    -0.50
     SearchView
    -0.49
    ted
    -0.49
    SequentialGroup
    -0.42
     rues
    -0.41
     to
    -0.41
    on
    -0.41
    ليد
    -0.41
    POSITIVE LOGITS
     feats
    1.10
    GEBURTSDATUM
    1.04
    vellous
    1.01
    Impressive
    0.97
    Amazing
    0.96
    tagHelperRunner
    0.95
     achievements
    0.95
    amazing
    0.94
    tacular
    0.91
     AMAZING
    0.91
    Act Density 0.130%

    No Known Activations