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

    Neuronpedia

    INDEX
    Explanations

    assertive suggestions and recommendations

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

    preceding a modal auxiliary verb

    np_acts-logits-general · gemini-2.0-flash

    should be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mål
    -0.31
     때문
    -0.28
     största
    -0.27
    kháu
    -0.27
     medida
    -0.27
     quedar
    -0.27
    Th
    -0.26
     procedente
    -0.26
     rassemble
    -0.26
    才
    -0.26
    POSITIVE LOGITS
    الدراسه
    0.71
     مشين
    0.70
     ویکی‌پدی
    0.63
     оригіналу
    0.62
     laſſen
    0.61
     beſch
    0.60
     someday
    0.59
     müſſen
    0.59
    <unused16>
    0.59
    <unused79>
    0.59
    Act Density 0.277%

    No Known Activations