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

    Neuronpedia

    INDEX
    Explanations

    percentages and quantifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಜು
    0.42
     tačiau
    0.41
     pacientes
    0.40
     acepta
    0.40
    很多人
    0.39
     grac
    0.39
     dels
    0.39
     epist
    0.38
    globin
    0.38
     sanguine
    0.38
    POSITIVE LOGITS
     addirittura
    0.48
     irgende
    0.46
    至少
    0.46
    或
    0.44
     irgend
    0.43
     zelfs
    0.42
     Employer
    0.41
     algún
    0.41
     Wyoming
    0.41
     Illinois
    0.40
    Act Density 0.026%

    No Known Activations