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

    Neuronpedia

    INDEX
    Explanations

    surprisingly complex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     undoubtedly
    1.21
     Конечно
    1.17
    ри
    1.11
     unquestionably
    1.03
     tentunya
    1.02
     eventuali
    1.02
     Essentially
    1.01
     certainly
    0.99
     básicamente
    0.99
    Fantastic
    0.99
    POSITIVE LOGITS
    (?)
    1.23
     (?)
    1.17
     niet
    1.10
     nicht
    1.07
     didn
    1.04
     Poco
    1.04
     not
    1.03
     agak
    1.02
     وليس
    0.98
    nicht
    0.97
    Act Density 0.036%

    No Known Activations