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

    Neuronpedia

    INDEX
    Explanations

    markdown bolding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    1.68
    .
    1.66
     herself
    1.62
     method
    1.60
     himself
    1.60
    :
    1.59
     organisation
    1.54
     scheme
    1.53
     strategy
    1.53
     organised
    1.50
    POSITIVE LOGITS
     инфра
    2.52
     Кроме
    2.27
    Additionally
    2.26
     граду
    2.17
    یکن
    2.14
    rinsic
    2.11
     fizik
    2.09
     Essentially
    2.05
    Essentially
    2.03
     оно
    2.01
    Act Density 0.664%

    No Known Activations