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

    Neuronpedia

    INDEX
    Explanations

    non-english script and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dieser
    0.50
     لهذا
    0.48
     in
    0.47
     tego
    0.46
     dieses
    0.45
    Sigma
    0.44
     diesem
    0.44
     questo
    0.43
    in
    0.43
     opera
    0.43
    POSITIVE LOGITS
     adecuados
    0.54
     মধুর
    0.47
    υ
    0.47
     adecuadas
    0.47
    кови
    0.46
    ке
    0.46
    ودي
    0.45
    нару
    0.45
    𝐲
    0.44
    ठीक
    0.44
    Act Density 0.000%

    No Known Activations