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

    Neuronpedia

    INDEX
    Explanations

    prices and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rij
    0.48
     repris
    0.46
     Cez
    0.44
     পৃষ্ঠা
    0.43
     страницы
    0.43
     rij
    0.42
     urządzenia
    0.42
     Gérard
    0.42
     berhubungan
    0.42
     đen
    0.42
    POSITIVE LOGITS
    low
    0.46
    Hot
    0.44
    Savings
    0.44
    Key
    0.43
    argo
    0.43
    project
    0.42
    vs
    0.42
    hot
    0.42
    side
    0.42
    Side
    0.41
    Act Density 0.001%

    No Known Activations