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

    Neuronpedia

    INDEX
    Explanations

    various mentions or references to systems

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

    describing systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __':
    -0.53
    __':
    -0.43
    )}_
    -0.42
     pleaſure
    -0.42
     Deiner
    -0.42
    cartItems
    -0.40
    ().__
    -0.39
    __":
    -0.39
     completing
    -0.38
    beli
    -0.38
    POSITIVE LOGITS
    OGND
    0.57
     CreateTagHelper
    0.55
    richTextPanel
    0.50
     idéia
    0.50
     للمعارف
    0.47
    Aiheesta
    0.47
     systeem
    0.46
     FetchType
    0.45
    archiviato
    0.44
    SequentialGroup
    0.43
    Act Density 0.071%

    No Known Activations