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

    Neuronpedia

    INDEX
    Explanations

    punctuation that marks the end of sentences

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

    ellipses and legal terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    发表于
    -0.61
     másik
    -0.57
    Билгалдахарш
    -0.56
    postsleuth
    -0.54
     Turquía
    -0.51
    CurrentValue
    -0.51
    caneca
    -0.51
    諉
    -0.50
    adesivo
    -0.49
     westfalen
    -0.48
    POSITIVE LOGITS
     .
    0.83
    ldots
    0.57
     ..
    0.56
    |.
    0.55
     ...
    0.54
    _.
    0.51
     {.
    0.50
     )
    0.49
     ....
    0.49
    ..
    0.49
    Act Density 0.008%

    No Known Activations