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

    Neuronpedia

    INDEX
    Explanations

    class declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    thisTrack
    0.28
    hydrox
    0.24
     sickly
    0.24
    westen
    0.24
     powdery
    0.24
    openhagen
    0.23
    allelujah
    0.23
    vertebr
    0.23
    methylsulfanyl
    0.23
    ethylsulfanyl
    0.23
    POSITIVE LOGITS
    Module
    0.32
    Factory
    0.32
    执行
    0.30
    子
    0.29
    Config
    0.29
     utils
    0.29
    类
    0.29
     factories
    0.28
    工厂
    0.28
    Delegate
    0.28
    Act Density 1.171%

    No Known Activations