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

    Neuronpedia

    INDEX
    Explanations

    the word "down" in various contexts, particularly emphasizing downward movement or transitions

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

    up and down movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prefier
    -0.33
     okaza
    -0.33
     révé
    -0.33
     quæ
    -0.32
    ĝis
    -0.32
    रीद
    -0.32
    将其
    -0.31
    例文帳に追加
    -0.31
    reveal
    -0.30
     Stadtteil
    -0.30
    POSITIVE LOGITS
    UpDown
    0.86
    AsUp
    0.82
    ThroughAttribute
    0.69
    AndEndTag
    0.69
    UpdateCommand
    0.68
    Personensuche
    0.65
    GraphicsUnit
    0.63
    帖最后由
    0.60
     مشين
    0.60
     Мексичка
    0.58
    Act Density 0.006%

    No Known Activations