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

    Neuronpedia

    INDEX
    Explanations

    periods at the end of sentences

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

    console output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.84
     мәкал
    -0.73
    ésultats
    -0.69
    bootstrapcdn
    -0.69
     nonUne
    -0.69
    principalColumn
    -0.68
    ValueStyle
    -0.67
    parsedMessage
    -0.67
     Roskov
    -0.66
    الحياه
    -0.66
    POSITIVE LOGITS
     
    0.42
    console
    0.38
     set
    0.37
                                   
    0.37
    ↵
    0.35
    ;
    0.35
    !
    0.34
     console
    0.34
      
    0.33
     natural
    0.33
    Act Density 0.001%

    No Known Activations