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

    Neuronpedia

    INDEX
    Explanations

    mentions of data format specifications

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

    format test

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UserScript
    -0.39
    ThemeProvider
    -0.38
    ')}}">
    -0.37
    では
    -0.33
     Hayashi
    -0.31
     Pfe
    -0.31
    PostId
    -0.30
    ｮ
    -0.30
    jel
    -0.30
    残
    -0.30
    POSITIVE LOGITS
     format
    3.00
    format
    2.97
     Format
    2.81
     formats
    2.73
    Format
    2.72
     Formats
    2.64
    formats
    2.64
     FORMAT
    2.59
    FORMAT
    2.42
    Formats
    2.39
    Act Density 0.007%

    No Known Activations