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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social media interactions and recognition

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

    Text preceding words like "with", "and", "for", or "on"

    np_acts-logits-general · gemini-2.0-flash

    news headlines and media topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.87
     فريبيس
    -0.86
     ModelExpression
    -0.84
    expandindo
    -0.81
     Савезне
    -0.79
    :✨
    -0.79
    GEBURTSDATUM
    -0.78
    ConstraintMaker
    -0.76
     saites
    -0.76
    NamedQueries
    -0.75
    POSITIVE LOGITS
     [
    0.80
     |
    0.71
    youtu
    0.58
    │
    0.54
    |
    0.53
    ⋆
    0.51
    <eos>
    0.49
     -
    0.49
    [
    0.47
    VIDEO
    0.47
    Act Density 0.163%

    No Known Activations