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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming and data structures

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

    Code snippets with brackets or parentheses

    np_acts-logits-general · gemini-2.0-flash

    code and mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.69
    featureID
    -0.58
    GEBURTSDATUM
    -0.56
     '\\;'
    -0.56
    AccessorTable
    -0.55
    MessageOf
    -0.55
     <>",
    -0.55
    sizeCache
    -0.54
    RTSC
    -0.52
     kiệm
    -0.51
    POSITIVE LOGITS
    endregion
    0.36
     unique
    0.36
    Sep
    0.34
    씌
    0.34
    leur
    0.32
     distracted
    0.32
    their
    0.32
     promising
    0.32
     written
    0.32
    unique
    0.32
    Act Density 0.726%

    No Known Activations