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

    Neuronpedia

    INDEX
    Explanations

    references to academic papers and articles related to research work

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

    academic paper introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.50
    ScopeManager
    -0.49
     typelib
    -0.48
    OuterClass
    -0.43
     coro
    -0.42
     Lightboxes
    -0.41
     CVT
    -0.41
    HtmlAttribute
    -0.41
    Equ
    -0.40
    esh
    -0.40
    POSITIVE LOGITS
    LinkId
    0.45
    Here
    0.44
     Here
    0.40
     disini
    0.40
     Aquí
    0.40
    BindView
    0.39
    RunWith
    0.39
     loisirs
    0.38
     here
    0.37
     herein
    0.37
    Act Density 0.044%

    No Known Activations