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

    Neuronpedia

    INDEX
    Explanations

    actions related to data manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bagaimana
    0.15
     essendo
    0.15
     ruhig
    0.14
    はや
    0.14
     אף
    0.14
    appen
    0.14
    規模
    0.14
     yattha
    0.14
     bahkan
    0.13
    CloseOperation
    0.13
    POSITIVE LOGITS
     them
    0.31
     into
    0.27
     it
    0.27
     onto
    0.25
     the
    0.23
     two
    0.21
     an
    0.21
    into
    0.21
     a
    0.21
     several
    0.21
    Act Density 0.463%

    No Known Activations