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

    Neuronpedia

    INDEX
    Explanations

    terms related to education and educational initiatives

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

    sentence beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.85
    InjectAttribute
    -0.85
    <unused15>
    -0.84
    <unused47>
    -0.84
    <unused16>
    -0.84
    <unused3>
    -0.84
    <unused41>
    -0.84
    <unused42>
    -0.84
    <unused23>
    -0.84
    <unused14>
    -0.84
    POSITIVE LOGITS
     notícia
    0.35
     news
    0.34
     News
    0.30
     sp
    0.27
     NEWS
    0.26
    NEWS
    0.25
    —
    0.23
     threat
    0.23
     notícias
    0.23
    news
    0.23
    Act Density 0.000%

    No Known Activations