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

    Neuronpedia

    INDEX
    Explanations

    thematic elements related to legal or contractual obligations

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

    Preceding the word "be" or a "to be" verb

    np_acts-logits-general · gemini-2.0-flash

    to be or is, in many languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.65
    JNIEnv
    -0.57
     EconPapers
    -0.55
    MethodManager
    -0.54
    &&\
    -0.49
    forKey
    -0.48
    Przypisy
    -0.48
     typelib
    -0.48
    MÁS
    -0.46
    ]++;
    -0.46
    POSITIVE LOGITS
    เป็น
    1.35
     là
    1.32
     adalah
    1.21
     является
    1.15
     is
    1.15
     merupakan
    1.10
     είναι
    1.06
    是个
    1.04
    是一个
    1.04
    是一個
    1.03
    Act Density 0.916%

    No Known Activations