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

    Neuronpedia

    INDEX
    Explanations

    Confluence, DevExtreme, Streamlit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    шава
    0.36
    _
    0.32
    Featured
    0.31
     मुहिम
    0.31
    -
    0.31
    у
    0.30
    ões
    0.29
    ává
    0.29
    하지만
    0.28
     thok
    0.28
    POSITIVE LOGITS
     with
    0.29
     blackened
    0.28
    IServerGame
    0.28
     ベージュ
    0.27
     painfully
    0.27
     グレー
    0.27
    強力
    0.27
     با
    0.27
    aconda
    0.26
     jeden
    0.26
    Act Density 0.100%

    No Known Activations