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

    Neuronpedia

    INDEX
    Explanations

    dealerships and their sourcing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Some
    1.00
    Map
    0.95
    Cloud
    0.95
    Human
    0.94
    more
    0.89
    Context
    0.88
    Small
    0.88
    it
    0.87
    Sur
    0.87
    Crit
    0.87
    POSITIVE LOGITS
     incorpora
    0.86
     purchase
    0.84
     booty
    0.82
     possession
    0.82
     keepsake
    0.81
     penchant
    0.80
     conces
    0.77
     possessions
    0.76
     coqu
    0.76
     esc
    0.76
    Act Density 0.000%

    No Known Activations