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

    Neuronpedia

    INDEX
    Explanations

    bracketed references or citations within the text

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

    [@ ref, bib, or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.65
    جغرافيا
    -0.49
     rhestr
    -0.48
     informée
    -0.44
     مرئيه
    -0.44
    WithFormat
    -0.40
    PROLOG
    -0.40
     ſtre
    -0.40
     चीज़ों
    -0.40
    ')))
    -0.39
    POSITIVE LOGITS
    [
    0.82
     }^{[
    0.82
    ,[
    0.61
    最快更新
    0.55
    ^{[
    0.54
    ❋
    0.53
    _{[
    0.53
    Rptr
    0.53
    orkin
    0.51
    loger
    0.50
    Act Density 0.012%

    No Known Activations