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

    Neuronpedia

    INDEX
    Explanations

    streamlit app

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     terceiro
    0.42
    ૐ
    0.42
     terzo
    0.41
    бки
    0.41
    ћи
    0.40
     tds
    0.37
    ۂ
    0.37
     час
    0.37
     dni
    0.36
    লাল
    0.36
    POSITIVE LOGITS
    app
    0.43
    ATION
    0.41
    ATIONS
    0.39
     rationality
    0.38
    ritual
    0.38
    spring
    0.38
     interf
    0.38
     contentment
    0.37
    valu
    0.37
    relaxed
    0.37
    Act Density 0.001%

    No Known Activations