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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to processes and methods in various contexts

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

    both or two

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -0.48
     rhestr
    -0.46
    mybatisplus
    -0.42
     QtWidgets
    -0.40
    protoimpl
    -0.40
    verifyException
    -0.40
    parseLong
    -0.40
    makeConstraints
    -0.39
    setViewName
    -0.39
     AllAfrica
    -0.38
    POSITIVE LOGITS
    Afterwards
    0.45
     Lightboxes
    0.45
     intermission
    0.43
    はじめに
    0.43
     Afterward
    0.42
     sonra
    0.42
     afterwards
    0.42
     Afterwards
    0.41
     afterward
    0.41
     nachher
    0.40
    Act Density 0.100%

    No Known Activations