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

    Neuronpedia

    INDEX
    Explanations

    continuous whitespace or empty sections in text

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

    Sentences or phrases that begin with "It"

    np_acts-logits-general · gemini-2.0-flash

    numbers and counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -0.85
     estekak
    -0.84
    setViewName
    -0.83
     autorytatywna
    -0.82
     Seeder
    -0.80
    RectangleBorder
    -0.79
     GenerationType
    -0.79
    __":
    -0.79
    DockStyle
    -0.78
    bootstrapcdn
    -0.77
    POSITIVE LOGITS
    ↵↵
    1.34
    ↵↵↵
    1.02
     Also
    0.76
    ↵↵↵↵↵
    0.76
    ↵↵↵↵
    0.75
     It
    0.74
     They
    0.74
     This
    0.73
    <eos>
    0.73
     The
    0.72
    Act Density 0.132%

    No Known Activations