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

    Neuronpedia

    INDEX
    Explanations

    numbers and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Най
    0.30
    Види
    0.29
    Сма
    0.28
    ный
    0.27
    気づ
    0.26
    Tapi
    0.26
    )}(\
    0.25
    Воз
    0.25
    Domic
    0.25
    Introduceti
    0.25
    POSITIVE LOGITS
     About
    0.27
     os
    0.27
     serializer
    0.26
    υ
    0.25
    ">→</
    0.25
     अंगों
    0.25
     Terms
    0.25
     stan
    0.25
     रिमाइंडर
    0.25
     від
    0.25
    Act Density 0.424%

    No Known Activations