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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and structured data elements in text

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

    abstract syntax trees or comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -1.34
    -1.05
     AssemblyCulture
    -1.05
    нгред
    -1.04
    хьтан
    -1.04
     queſta
    -1.02
     Geſch
    -1.02
    ########.
    -1.00
    afficheront
    -1.00
    principalColumn
    -1.00
    POSITIVE LOGITS
    1
    0.44
    2
    0.41
    I
    0.41
    0
    0.39
    4
    0.36
    ↵↵↵
    0.35
    7
    0.35
    .
    0.35
    type
    0.34
    E
    0.34
    Act Density 0.027%

    No Known Activations