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

    Neuronpedia

    INDEX
    Explanations

    defining code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OpportunitiesBy
    0.45
    fühl
    0.39
    KindOfClass
    0.38
     inglesa
    0.38
     condem
    0.37
    沸
    0.37
    Thou
    0.36
     conlleva
    0.36
     ovog
    0.36
     veröffentlicht
    0.35
    POSITIVE LOGITS
     Define
    1.02
     define
    0.91
    Define
    0.84
    define
    0.77
     Create
    0.75
     create
    0.73
     Defining
    0.71
     定义
    0.68
     Initialize
    0.66
     defining
    0.64
    Act Density 0.043%

    No Known Activations