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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating obligation or necessity

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

    conditional clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     faſt
    -0.48
     Anſ
    -0.45
     houſe
    -0.45
     يتيمه
    -0.43
     Inſ
    -0.42
     Conſ
    -0.40
     Houſe
    -0.39
     laſt
    -0.39
     Reſ
    -0.38
     ſeveral
    -0.38
    POSITIVE LOGITS
    /**
    0.69
    BagLayout
    0.65
     ModelExpression
    0.62
    rungsseite
    0.59
    posedge
    0.58
     sofern
    0.57
     Paglinawan
    0.56
     AssemblyCulture
    0.56
     resourceCulture
    0.55
    󠁢
    0.55
    Act Density 0.024%

    No Known Activations