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

    Neuronpedia

    INDEX
    Explanations

    describing items or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rumors
    0.46
     flavorful
    0.45
     rumor
    0.45
     cognizant
    0.43
     licensure
    0.42
     randomized
    0.40
     DOJ
    0.39
    ◦
    0.39
     দেয়ার
    0.39
     outfitted
    0.38
    POSITIVE LOGITS
     tyres
    0.69
     fertiliser
    0.66
     dodgy
    0.64
     Sainsbury
    0.63
     tyre
    0.61
     trousers
    0.60
     prawn
    0.59
     fertilisers
    0.59
     (£
    0.58
     Tesco
    0.58
    Act Density 0.028%

    No Known Activations