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

    Neuronpedia

    INDEX
    Explanations

    punctuations marking the end of statements or quotations

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

    Immediately precedes or is a punctuation mark

    np_acts-logits-general · gemini-2.0-flash

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.84
    endphp
    -0.83
     snippetHide
    -0.82
    </caption>
    -0.73
    UnitTesting
    -0.73
    Hozzáférés
    -0.72
    الحياه
    -0.70
    AnchorStyles
    -0.68
     Мексичка
    -0.68
     GenerationType
    -0.67
    POSITIVE LOGITS
    <eos>
    0.76
    なお
    0.70
     Earlier
    0.64
    Earlier
    0.62
     The
    0.57
     earlier
    0.57
    <bos>
    0.56
     Currently
    0.56
     cabe
    0.56
    ちなみに
    0.55
    Act Density 0.147%

    No Known Activations