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

    Neuronpedia

    INDEX
    Explanations

    communication methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    őt
    0.47
    ará
    0.46
    DT
    0.46
    nél
    0.45
    ેલા
    0.42
     убы
    0.42
    na
    0.41
    UR
    0.41
    MIT
    0.41
     extravag
    0.41
    POSITIVE LOGITS
    াণিত
    0.48
     পানি
    0.48
     پانی
    0.48
     पानी
    0.47
     Bick
    0.46
     tipping
    0.46
     Apprentice
    0.44
     Instructional
    0.44
     वृद्धि
    0.43
     deutscher
    0.43
    Act Density 0.006%

    No Known Activations