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

    Neuronpedia

    INDEX
    Explanations

    place names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     논
    0.54
    논
    0.52
     logically
    0.50
     들
    0.47
     pot
    0.44
     언
    0.44
     nj
    0.43
    論
    0.41
    Pol
    0.40
    experiments
    0.40
    POSITIVE LOGITS
     قائ
    0.43
    েইল
    0.40
    압
    0.39
    వేశ
    0.39
     hairy
    0.39
     außerdem
    0.39
     yeah
    0.38
    жаем
    0.38
    wah
    0.38
    虏
    0.38
    Act Density 0.002%

    No Known Activations