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

    Neuronpedia

    INDEX
    Explanations

    charges, redundant, building, brand, journal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     licenciatura
    1.22
    라이
    1.19
     ngờ
    1.15
    ल्डेन
    1.15
    رويج
    1.11
    en
    1.09
     sellest
    1.09
    ничный
    1.09
    는지
    1.09
    sini
    1.08
    POSITIVE LOGITS
    𝒓
    1.47
    𝒊
    1.44
    𝙞
    1.43
    𝒎
    1.30
    𝒖
    1.26
    𝙛
    1.25
    𝙪
    1.24
    𝙨
    1.24
    ما
    1.22
    𝙜
    1.18
    Act Density 0.001%

    No Known Activations