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

    Neuronpedia

    INDEX
    Explanations

    references to complex economic or business concepts, particularly those involving schemes or financial strategies

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

    scheme and promises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     some
    -0.25
     (
    -0.23
     females
    -0.23
     hard
    -0.23
     type
    -0.22
    }
    -0.22
     female
    -0.21
     недорого
    -0.21
     more
    -0.20
     Demokratie
    -0.20
    POSITIVE LOGITS
     kaarangay
    0.92
     estekak
    0.86
     Reſ
    0.82
     ModelExpression
    0.82
     好文分享
    0.81
     Meksiku
    0.80
     メンテナ
    0.80
    <unused19>
    0.79
    <unused7>
    0.79
    <unused3>
    0.79
    Act Density 0.023%

    No Known Activations