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

    Neuronpedia

    INDEX
    Explanations

    words or phrases expressing positive sentiment, good fortune or appreciation.

    oai_token-act-pair · gemini-2.0-flash

    lucky/fortunate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enumi
    -0.68
     luck
    -0.66
     lucky
    -0.65
     LUCK
    -0.61
    lucky
    -0.61
     fortunate
    -0.57
    ISupport
    -0.56
    OrNil
    -0.56
    SourceChecksum
    -0.52
    Lucky
    -0.50
    POSITIVE LOGITS
    IonicModule
    0.57
     conclure
    0.52
    antaranya
    0.52
    sidemargin
    0.52
    nología
    0.52
    DataAnnotations
    0.51
     catatan
    0.51
     stället
    0.50
    bebasan
    0.50
    ituary
    0.50
    Act Density 15.321%

    No Known Activations