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

    Neuronpedia

    INDEX
    Explanations

    food ingredients and objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FocusValue
    0.56
    靠
    0.47
     вересня
    0.47
    ﻥ
    0.45
    是一个
    0.45
    是一個
    0.45
    价值
    0.44
    很少
    0.44
    蠢
    0.44
    藜
    0.44
    POSITIVE LOGITS
     கோ
    0.47
     remodeling
    0.45
    hydrox
    0.45
     detectable
    0.44
    hotite
    0.44
     maintenance
    0.43
    しくは
    0.43
     उत्सर्जन
    0.43
    orestation
    0.43
     ដើម្បី
    0.42
    Act Density 0.001%

    No Known Activations