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

    Neuronpedia

    INDEX
    Explanations

    phrases related to advice or suggestions in a structured format

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

    Code, commands, and non-English words

    np_acts-logits-general · gemini-2.0-flash

    `Sterol`, code, `get`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RefNanny
    -0.64
     estimés
    -0.61
    AsUp
    -0.60
    ifrance
    -0.55
     chestnuts
    -0.53
     <>",
    -0.52
    erton
    -0.51
    _,
    -0.47
    IBOutlet
    -0.47
    otheby
    -0.47
    POSITIVE LOGITS
     مشين
    0.58
     ролях
    0.54
    циях
    0.53
    orah
    0.50
    никах
    0.49
    ukkig
    0.49
    calyp
    0.48
    matchCondition
    0.47
    नो
    0.47
    krivning
    0.47
    Act Density 0.087%

    No Known Activations