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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases that start a new section or topic

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

    Non-English words or code snippets

    np_acts-logits-general · gemini-2.0-flash

    listing items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.58
     H
    -0.52
     كومونز
    -0.51
    les
    -0.50
    cet
    -0.48
     الحره
    -0.47
    |
    -0.46
     (
    -0.46
     az
    -0.45
     
    -0.44
    POSITIVE LOGITS
    WriteTagHelper
    0.80
     iſt
    0.78
     мәкал
    0.78
    клопе
    0.78
    sidemargin
    0.78
     myſelf
    0.77
     ―――――
    0.76
     itſelf
    0.76
     Monfieur
    0.76
     ſy
    0.71
    Act Density 1.204%

    No Known Activations