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

    Neuronpedia

    INDEX
    Explanations

    Categories or entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    мии
    0.35
     он
    0.34
    робнее
    0.33
    ليات
    0.33
    әне
    0.33
    нки
    0.32
     政府
    0.31
     cosidd
    0.31
    来看看
    0.30
    ктери
    0.30
    POSITIVE LOGITS
     Highlight
    0.36
     panoramic
    0.35
     provides
    0.35
     xc
    0.35
     highlighting
    0.33
     r
    0.32
     Provides
    0.32
     minimalistic
    0.32
     Th
    0.31
     characterized
    0.31
    Act Density 0.008%

    No Known Activations