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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their occurrences in a specified context

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

    Object member access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedCtor
    -0.69
     يتيمه
    -0.69
     createState
    -0.69
     increí
    -0.68
    MigrationBuilder
    -0.67
     queſta
    -0.66
    majánló
    -0.64
     disambiguazione
    -0.63
    antaranya
    -0.63
     ainfi
    -0.62
    POSITIVE LOGITS
     
    0.53
     \
    0.48
    s
    0.47
    copyOf
    0.46
    ↵↵
    0.45
     $
    0.45
     grossly
    0.44
    ↵
    0.43
     completely
    0.42
     L
    0.41
    Act Density 0.011%

    No Known Activations