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

    Neuronpedia

    INDEX
    Explanations

    research interests and focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     accountants
    0.46
     salespeople
    0.46
     davvero
    0.43
     businessmen
    0.42
     డబ్బు
    0.42
     sadece
    0.42
     supremely
    0.41
     geniuses
    0.41
     dinheiro
    0.40
     훨씬
    0.39
    POSITIVE LOGITS
     interested
    0.68
     interests
    0.64
     research
    0.63
     관심
    0.62
    interests
    0.62
     tertarik
    0.62
     interesa
    0.61
     fascinated
    0.60
     specializes
    0.59
     currently
    0.58
    Act Density 0.013%

    No Known Activations