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

    Neuronpedia

    INDEX
    Explanations

    elements related to user interface components in code snippets

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

    code and mathematical symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uží
    -0.31
    でも
    -0.29
    起来
    -0.27
     res
    -0.26
    công
    -0.26
    起來
    -0.26
    Lycka
    -0.25
     thus
    -0.25
    สุข
    -0.25
     Res
    -0.24
    POSITIVE LOGITS
    ArrowToggle
    0.77
     للمعارف
    0.75
     يتيمه
    0.73
    principalColumn
    0.66
    BufferException
    0.64
    IContainer
    0.64
    tagHelperRunner
    0.63
    SequentialGroup
    0.62
    tonode
    0.62
     estekak
    0.61
    Act Density 0.001%

    No Known Activations