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

    Neuronpedia

    INDEX
    Explanations

    action followed by completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ್
    0.42
    maine
    0.41
     documents
    0.40
    發現
    0.39
     दस्तावेजों
    0.39
    读
    0.39
     documentos
    0.38
     documento
    0.38
     Texans
    0.38
    लरशिप
    0.36
    POSITIVE LOGITS
    🌭
    0.39
     pyrid
    0.38
     🤗
    0.38
     bý
    0.38
     चौथ
    0.38
     African
    0.37
    🍜
    0.36
    🏕
    0.36
    💂
    0.36
    முகச்
    0.36
    Act Density 0.000%

    No Known Activations