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

    Neuronpedia

    INDEX
    Explanations

    the key is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ாவின்
    0.35
    personality
    0.35
     Tekn
    0.35
    çok
    0.33
     Flame
    0.33
     berupa
    0.33
    𝐗
    0.32
     subway
    0.32
     Redmi
    0.32
     Russie
    0.32
    POSITIVE LOGITS
     thing
    0.36
     هنا
    0.33
    들
    0.33
     факт
    0.32
    អ្វី
    0.32
     rằng
    0.31
     કે
    0.31
     ότι
    0.31
     أن
    0.30
     여기서
    0.29
    Act Density 0.086%

    No Known Activations