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

    Neuronpedia

    INDEX
    Explanations

    phrases related to communication or connection processes

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

    communication channels

    np_acts-logits-general · gemini-2.0-flash

    communicating channels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bomb
    -0.43
     tent
    -0.42
    stock
    -0.42
     matin
    -0.41
     disambiguazione
    -0.41
     stock
    -0.40
     tri
    -0.40
    Bomb
    -0.40
    bomb
    -0.40
    декса
    -0.39
    POSITIVE LOGITS
     channel
    3.47
    channel
    3.13
     Channel
    3.04
    Channel
    2.89
     CHANNEL
    2.71
    CHANNEL
    2.52
     channels
    2.50
     Channels
    2.23
    getChannel
    2.12
    channels
    2.10
    Act Density 0.142%

    No Known Activations