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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate memory, recall, and reminders related to information

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

    recall and remember facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Party
    -0.40
     Bukit
    -0.38
    Mgmt
    -0.37
     party
    -0.36
     ass
    -0.36
    سكر
    -0.36
     opti
    -0.36
    seg
    -0.35
     ward
    -0.35
    theoremstyle
    -0.35
    POSITIVE LOGITS
    Напомним
    0.80
     disambiguazione
    0.66
     connus
    0.60
     <<<<<<<<<<<<<<
    0.59
    دانشنامهٔ
    0.58
    RTGC
    0.58
     connues
    0.56
     diketahui
    0.56
    ISupport
    0.55
    InputTagHelper
    0.55
    Act Density 0.006%

    No Known Activations