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

    Neuronpedia

    INDEX
    Explanations

    LaTeX commands and formatting elements

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

    summary and abstract

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.80
     مشين
    -0.66
     padx
    -0.63
     Winaray
    -0.63
     inflater
    -0.62
    errHandler
    -0.62
     sumpay
    -0.60
    DockStyle
    -0.60
    arraycopy
    -0.59
     bezeichneter
    -0.59
    POSITIVE LOGITS
    abstract
    0.58
    Abstract
    0.55
     abstract
    0.46
     Abstract
    0.42
    Summary
    0.42
     abstracta
    0.40
    Abstra
    0.39
    摘要
    0.37
    summary
    0.36
     toiture
    0.36
    Act Density 0.002%

    No Known Activations