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

    Neuronpedia

    INDEX
    Explanations

    comparing multiple attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    indrome
    0.41
    ኩ
    0.41
    最好的
    0.41
    流行的
    0.40
    恋
    0.39
     فعالیت
    0.39
    រី
    0.38
    遊
    0.38
     utilizar
    0.38
     ምክንያ
    0.38
    POSITIVE LOGITS
     v
    0.45
     deserving
    0.38
    ους
    0.38
    уса
    0.38
    AppSettings
    0.38
    iad
    0.37
     caseload
    0.37
     clerks
    0.37
     crucial
    0.37
     PKC
    0.37
    Act Density 0.001%

    No Known Activations