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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bec
    -0.08
     cir
    -0.07
     TOR
    -0.06
    HERE
    -0.06
    .fre
    -0.06
     TOTAL
    -0.06
    ค
    -0.06
     TWO
    -0.06
     prestigious
    -0.06
    _Tree
    -0.06
    POSITIVE LOGITS
     uten
    0.07
     didn
    0.07
     Offer
    0.06
     poskyt
    0.06
     listView
    0.06
     offer
    0.06
    лаг
    0.06
    tract
    0.06
     stav
    0.06
     Offers
    0.06
    Act Density 0.003%

    No Known Activations