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

    Neuronpedia

    INDEX
    Explanations

    defining extensions, models, signals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    meyen
    0.48
    NumberOf
    0.47
     तीसरे
    0.47
     уверен
    0.47
    izure
    0.44
     TOEFL
    0.43
     accur
    0.43
     nyug
    0.43
    unky
    0.42
     conseguido
    0.42
    POSITIVE LOGITS
     primitives
    0.63
     primitive
    0.58
    Component
    0.56
    Streams
    0.54
     Component
    0.53
     plugins
    0.52
     monadic
    0.52
     plugin
    0.51
     pipelines
    0.51
    Context
    0.50
    Act Density 0.032%

    No Known Activations