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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to conjunctions and articles

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

    and when

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.49
     QtWidgets
    -0.47
     صوتيه
    -0.46
    risto
    -0.44
     kasarigan
    -0.44
    期刊论文
    -0.43
    mybatisplus
    -0.42
    adpleegd
    -0.42
    tagonal
    -0.42
    atshirt
    -0.41
    POSITIVE LOGITS
    GenerationType
    0.48
     gdy
    0.43
     where
    0.43
    BeginContext
    0.42
    when
    0.40
     kiedy
    0.40
     lorsque
    0.39
     when
    0.39
     जब
    0.38
     GenerationType
    0.38
    Act Density 0.188%

    No Known Activations