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

    Neuronpedia

    INDEX
    Explanations

    identifiers and labels used in structured data formats, such as APIs or databases

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

    Colon punctuation

    np_acts-logits-general · gemini-2.0-flash

    file path indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onAnimation
    -0.85
    TargetException
    -0.78
     bodyParser
    -0.65
     Shakspeare
    -0.63
     noqa
    -0.62
    ArgsConstructor
    -0.58
    stylers
    -0.58
    PostExecute
    -0.58
     numberOfRows
    -0.56
     LOGGER
    -0.56
    POSITIVE LOGITS
    filepath
    0.60
     filepath
    0.60
    tvguidetime
    0.57
    
    0.55
    expandindo
    0.53
    
    0.53
     facilite
    0.53
     avent
    0.53
     виправивши
    0.52
    limsy
    0.51
    Act Density 0.073%

    No Known Activations