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

    Neuronpedia

    INDEX
    Explanations

    market, animal, phone, entity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    У
    1.10
    вЂ
    1.04
    selves
    1.04
     discour
    1.03
     ponder
    1.03
    𝒾
    1.00
     precaution
    0.99
     locality
    0.99
     sacrificed
    0.98
     по
    0.98
    POSITIVE LOGITS
    ب
    1.21
    cą
    1.19
    د
    1.16
    ϱ
    1.13
    éu
    1.07
     üç
    1.06
    żej
    1.05
    ar
    1.05
    াসের
    1.04
    álně
    1.03
    Act Density 0.004%

    No Known Activations