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

    Neuronpedia

    INDEX
    Explanations

    mathematical constructs and relationships within graphs and sets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical notation and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     working
    -0.32
    nextDouble
    -0.32
    ToMany
    -0.31
     WORKING
    -0.30
     passing
    -0.29
    piet
    -0.28
     pass
    -0.28
     do
    -0.28
    かしい
    -0.28
    BoxLayout
    -0.28
    POSITIVE LOGITS
    :✨
    0.66
    MessageTagHelper
    0.64
     betweenstory
    0.64
     ErrIntOverflow
    0.61
    msgTypes
    0.57
     esternos
    0.55
    ніципа
    0.54
     Italijani
    0.53
    ſelves
    0.53
     kasarigan
    0.52
    Act Density 0.106%

    No Known Activations