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

    Neuronpedia

    INDEX
    Explanations

    as potential or consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conversa
    0.89
     interaction
    0.75
     conversations
    0.75
     разгово
    0.73
     conversation
    0.71
     ısı
    0.71
     interactions
    0.71
    ialog
    0.70
     matematica
    0.68
     libre
    0.68
    POSITIVE LOGITS
    Din
    0.86
     Defts
    0.82
    Relative
    0.82
     Relative
    0.80
    Menurut
    0.79
    Roots
    0.79
     Valuation
    0.78
     Feature
    0.78
    Directory
    0.77
    Profit
    0.77
    Act Density 0.000%

    No Known Activations