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

    Neuronpedia

    INDEX
    Explanations

    start of turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਸ
    0.48
     Dieser
    0.47
     králov
    0.46
     타고
    0.44
     Approx
    0.43
     Και
    0.43
     früheren
    0.42
    ASX
    0.41
    Major
    0.41
    shoz
    0.41
    POSITIVE LOGITS
     (
    0.52
    0.47
     editors
    0.38
     у
    0.38
     pigments
    0.38
     refinements
    0.38
     gases
    0.37
     sides
    0.37
     exh
    0.37
     as
    0.37
    Act Density 0.001%

    No Known Activations