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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating movement or change

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

    come with or from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -0.60
     Infór
    -0.59
     Wikiseite
    -0.55
    eseorang
    -0.54
    Personensuche
    -0.53
    UserScript
    -0.52
    migrationBuilder
    -0.51
     hendak
    -0.49
    ambién
    -0.49
     ویکی‌پدی
    -0.48
    POSITIVE LOGITS
    inherits
    0.48
    galus
    0.44
     Who
    0.40
     Tomb
    0.40
     tom
    0.40
     Tom
    0.39
     Canal
    0.38
     Zon
    0.38
    <eos>
    0.37
     consequences
    0.37
    Act Density 0.053%

    No Known Activations