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

    Neuronpedia

    INDEX
    Explanations

    errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     പിന്തുണ
    0.38
     rộng
    0.37
     number
    0.35
     gla
    0.34
     Gla
    0.34
    Rewards
    0.34
     rewards
    0.33
     bows
    0.33
     үч
    0.33
    changes
    0.32
    POSITIVE LOGITS
    AgentError
    0.47
     कारण
    0.46
    لاء
    0.43
     manifestations
    0.43
    ފ
    0.41
     misfort
    0.40
     symptômes
    0.39
    getMessage
    0.38
    の原因
    0.38
    स्य
    0.38
    Act Density 0.007%

    No Known Activations