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

    Neuronpedia

    INDEX
    Explanations

    document formatting indicators, specifically the beginning of sections and hierarchical organization

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

    preceding various hyphenated words

    np_acts-logits-general · gemini-2.0-flash

    phrases starting with common adjectives or possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    -0.90
    ↵
    -0.88
    ↵↵
    -0.83
     […]
    -0.78
    ...
    -0.72
     
    -0.69
    …
    -0.69
     ...
    -0.68
     [...]
    -0.63
    -
    -0.62
    POSITIVE LOGITS
    rungsseite
    0.95
     تانيه
    0.91
    Datuak
    0.90
     ModelExpression
    0.88
     незавершена
    0.87
     Савезне
    0.84
     الحره
    0.81
     arşivlendi
    0.80
    HostException
    0.80
     تضيفلها
    0.80
    Act Density 0.000%

    No Known Activations