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

    Neuronpedia

    INDEX
    Explanations

    unique

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    িন
    2.35
    ור
    2.25
    杆
    2.19
     demeanor
    2.03
     nearest
    1.96
     coleg
    1.91
    сь
    1.90
    1.90
    municipal
    1.88
     وش
    1.86
    POSITIVE LOGITS
    সাধারণ
    2.78
     особенности
    2.32
    startsWith
    2.27
    𝚊
    2.23
    experiences
    2.22
     conjunction
    2.20
     Experiences
    2.19
    permitAll
    2.13
    তে
    2.13
     experiences
    2.09
    Act Density 0.124%

    No Known Activations