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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of distance or separation

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

    far from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HomeAsUpEnabled
    -0.47
    ModelAdmin
    -0.41
     GenerationType
    -0.40
     insuffisamment
    -0.39
     bParam
    -0.39
    InitVars
    -0.39
    SharedCtor
    -0.37
     fasse
    -0.36
    BagLayout
    -0.35
     anglès
    -0.34
    POSITIVE LOGITS
    :✨
    0.54
    期刊论文
    0.46
     ProtoMessage
    0.45
     NEVER
    0.44
    FAR
    0.44
    orghini
    0.43
    REJECT
    0.42
     Paglinawan
    0.42
    haupt
    0.41
     keineswegs
    0.41
    Act Density 0.211%

    No Known Activations