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

    Neuronpedia

    INDEX
    Explanations

    ellipses and punctuation marks indicating pauses or trailing thoughts

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

    Follows ellipses or incomplete sentences

    np_acts-logits-general · gemini-2.0-flash

    trailing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NUMX
    -0.98
    expandindo
    -0.96
    NewUrlParser
    -0.93
     للمعارف
    -0.81
     NSCoder
    -0.81
     autorytatywna
    -0.81
    Tikang
    -0.80
    bootstrapcdn
    -0.77
    CloseOperation
    -0.77
    SBATCH
    -0.75
    POSITIVE LOGITS
    ↵↵
    1.30
    ↵
    0.99
    ↵↵↵
    0.94
    <eos>
    0.93
     The
    0.79
    ↵↵↵↵
    0.79
    if
    0.76
     but
    0.76
    and
    0.75
    it
    0.73
    Act Density 0.113%

    No Known Activations