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

    Neuronpedia

    INDEX
    Explanations

    beyond human

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ㅔ
    0.46
     سط
    0.45
     اکثریت
    0.45
    ചി
    0.45
     লাই
    0.45
     חי
    0.44
    att
    0.43
     המו
    0.43
    ibo
    0.43
    Protocol
    0.42
    POSITIVE LOGITS
     exporters
    0.56
     suspensions
    0.52
     controllers
    0.52
    ёл
    0.52
     pairings
    0.51
    𝙠
    0.50
     Sart
    0.50
     stirring
    0.48
     organizations
    0.48
     beverages
    0.47
    Act Density 0.000%

    No Known Activations