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

    Neuronpedia

    INDEX
    Explanations

    sections or headings that indicate key information or references in documents

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

    followed by capitalized words

    np_acts-logits-general · gemini-2.0-flash

    section headings and formal language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الإنجليزية
    -0.99
    findpost
    -0.93
     Meksiku
    -0.90
    MigrationBuilder
    -0.85
     AssemblyProduct
    -0.83
     '\\;'
    -0.82
    Hochspringen
    -0.78
    istoitu
    -0.76
    AutoField
    -0.75
    Geografi
    -0.75
    POSITIVE LOGITS
    chdir
    0.41
     direta
    0.41
    Appear
    0.40
    ↵↵
    0.40
    iyle
    0.38
    Seeking
    0.38
    sikker
    0.38
     Seeking
    0.37
     chờ
    0.37
    Raises
    0.37
    Act Density 0.642%

    No Known Activations