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

    Neuronpedia

    INDEX
    Explanations

    punctuation and question-related marks

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

    expert advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.54
     protoimpl
    -0.52
     aDecoder
    -0.51
     Мексичка
    -0.48
    الحياه
    -0.47
     Савезне
    -0.47
    OGND
    -0.45
     newOwner
    -0.44
    #\
    -0.43
     fum
    -0.43
    POSITIVE LOGITS
    moveToFirst
    0.57
     <=",
    0.48
     recommendation
    0.47
     siguran
    0.47
     recomienda
    0.46
     argint
    0.46
    mappedBy
    0.45
     popolari
    0.45
     magnétique
    0.45
     recommends
    0.44
    Act Density 0.000%

    No Known Activations