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

    Neuronpedia

    INDEX
    Explanations

    Okay, you want to run

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    甑
    0.38
    श्यक
    0.38
    ὐ
    0.37
     ज्ञ
    0.37
     الانترنت
    0.37
    ഹ്ലാ
    0.37
    ുട
    0.37
     인터넷
    0.37
    ജ്യ
    0.37
    na
    0.36
    POSITIVE LOGITS
     articol
    0.40
    rosis
    0.37
     possible
    0.36
    смо
    0.35
    due
    0.35
    زم
    0.35
    ሪ
    0.35
     LU
    0.34
    ନ୍
    0.34
     कर्
    0.33
    Act Density 0.000%

    No Known Activations