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

    Neuronpedia

    INDEX
    Explanations

    markup-related syntax and HTML attributes

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

    Code snippets and file paths

    np_acts-logits-general · gemini-2.0-flash

    code and URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -1.09
    الحياه
    -1.04
    <unused28>
    -1.03
    <unused41>
    -1.03
    <unused14>
    -1.03
    [@BOS@]
    -1.03
    <unused16>
    -1.02
    <unused17>
    -1.02
    <unused8>
    -1.02
    <unused3>
    -1.02
    POSITIVE LOGITS
    usepackage
    0.41
    <eos>
    0.30
     Braut
    0.25
     frontera
    0.24
     companhia
    0.22
    ↵
    0.22
     tienda
    0.21
     amistad
    0.21
    y
    0.21
     fidèles
    0.21
    Act Density 0.009%

    No Known Activations