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

    Neuronpedia

    INDEX
    Explanations

    textual formatting and punctuation

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

    Starts with quotes or apostrophes

    np_acts-logits-general · gemini-2.0-flash

    apostrophes and contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enderror
    -0.71
     StringTokenizer
    -0.51
     autorytatywna
    -0.50
    ՚
    -0.49
     ChromeDriver
    -0.48
     progressBar
    -0.48
    hamshire
    -0.47
    oredCriteria
    -0.47
     addSubview
    -0.47
     Anſ
    -0.47
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.50
    ↵↵↵↵↵↵↵
    0.48
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.46
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.46
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.45
    ↵↵↵↵↵↵↵↵↵↵↵
    0.45
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.44
    ↵↵↵↵↵
    0.44
    ↵↵↵
    0.44
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.44
    Act Density 0.426%

    No Known Activations