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

    Neuronpedia

    INDEX
    Explanations

    references to dates and quantities

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

    numbers followed by time units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rxjs
    -0.54
    乓
    -0.50
    Numerade
    -0.50
    EditorBrowsable
    -0.50
     AppCompatTheme
    -0.46
    MongoClient
    -0.46
    pausal
    -0.45
    PERTIES
    -0.45
    findpost
    -0.45
     Walkover
    -0.44
    POSITIVE LOGITS
     kasarigan
    0.58
     voire
    0.40
     akár
    0.38
     jopa
    0.37
     even
    0.35
     ffilmiau
    0.34
    TRIBUN
    0.34
    Bahkan
    0.33
     dès
    0.33
     이미
    0.33
    Act Density 0.014%

    No Known Activations