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

    Neuronpedia

    INDEX
    Explanations

    a way to achieve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amoto
    0.45
    ada
    0.45
    etsu
    0.44
    ovo
    0.44
    ase
    0.43
    ue
    0.43
    ama
    0.43
    ac
    0.42
    c
    0.42
    Coin
    0.41
    POSITIVE LOGITS
     paradigma
    0.43
     König
    0.41
     Reaktion
    0.41
    푹
    0.40
     اٹ
    0.40
     adegu
    0.40
    ۔
    0.40
     Beiträge
    0.39
    烺
    0.39
    শ্চর্য
    0.39
    Act Density 0.001%

    No Known Activations