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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements

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

    Comes after punctuation that ends a sentence

    np_acts-logits-general · gemini-2.0-flash

    expressions of surprise or realization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RTLU
    -0.46
    تقاوى
    -0.45
    fromnode
    -0.42
    -0.41
    transQ
    -0.41
     protoimpl
    -0.39
    NameInMap
    -0.39
     censiti
    -0.39
    hability
    -0.38
    énario
    -0.38
    POSITIVE LOGITS
     wow
    1.02
     Wow
    1.00
     Hmmm
    0.94
    Wow
    0.94
    Yikes
    0.94
     Sounds
    0.93
    Sounds
    0.93
    wow
    0.91
     WOW
    0.91
    sounds
    0.89
    Act Density 0.444%

    No Known Activations