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

    Neuronpedia

    INDEX
    Explanations

    references to family relationships

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

    family relationships and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seems
    -0.42
    妥
    -0.41
     doesn
    -0.40
    Dost
    -0.40
     Italijanski
    -0.39
    这是一
    -0.38
     Dost
    -0.37
     подоб
    -0.37
    rogly
    -0.36
     trö
    -0.35
    POSITIVE LOGITS
    Personendaten
    0.64
    ConstraintMaker
    0.61
    帖最后由
    0.58
    rungsseite
    0.58
    Datuak
    0.56
    enumi
    0.54
     Wikimedijinoj
    0.54
    HasForeignKey
    0.51
    ArgsConstructor
    0.51
    AndEndTag
    0.51
    Act Density 0.020%

    No Known Activations