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

    Neuronpedia

    INDEX
    Explanations

    customer support satisfaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ανθρώ
    1.08
    يين
    1.01
    nesses
    1.00
    人間の
    1.00
    ीय
    0.98
    𝕤
    0.96
     ascribe
    0.96
     pâle
    0.96
    멩
    0.95
    clos
    0.95
    POSITIVE LOGITS
     sạn
    1.12
     satisfaction
    0.95
     Satisfaction
    0.92
    DI
    0.91
     magia
    0.91
     धरना
    0.87
     многочис
    0.86
     presto
    0.84
     Nagel
    0.84
     ombre
    0.84
    Act Density 0.295%

    No Known Activations