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

    Neuronpedia

    INDEX
    Explanations

    specific descriptors and queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </code>
    0.44
     Makeup
    0.39
    Opportunity
    0.38
    ↵
    0.38
    </b>
    0.37
     Opportunity
    0.36
    Makeup
    0.36
    R
    0.35
    ́
    0.35
    伸ば
    0.35
    POSITIVE LOGITS
     nigdy
    0.50
     スタッドレスタイヤ
    0.42
     wildlife
    0.42
     與
    0.42
     \%
    0.41
     znale
    0.40
    етки
    0.40
     sonora
    0.40
     splend
    0.39
    コミ
    0.39
    Act Density 0.001%

    No Known Activations