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

    Neuronpedia

    INDEX
    Explanations

    unlocking premium features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    льне
    0.47
    難
    0.44
    льном
    0.43
    圿
    0.41
    Ფ
    0.40
    льність
    0.38
    beforeend
    0.37
    初始化
    0.37
    льное
    0.37
    ByMerging
    0.36
    POSITIVE LOGITS
     premium
    0.88
     unlock
    0.86
     unlocking
    0.85
     unlocks
    0.79
     Premium
    0.78
    premium
    0.78
    解锁
    0.74
    unlock
    0.72
    Premium
    0.71
    Unlock
    0.70
    Act Density 0.009%

    No Known Activations