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

    Neuronpedia

    INDEX
    Explanations

    snippets of code and programming constructs

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

    Tokens after a lowercase letter

    np_acts-logits-general · gemini-2.0-flash

    code elements and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.42
    렀
    -0.38
     fre
    -0.37
     Sch
    -0.34
    tagHelper
    -0.33
    lerine
    -0.32
    shutil
    -0.32
     
    -0.31
     truly
    -0.31
     Alumni
    -0.30
    POSITIVE LOGITS
     AssemblyTitle
    0.82
     يتيمه
    0.79
     ModelExpression
    0.79
     Paglinawan
    0.73
    sizeCache
    0.73
    msgTypes
    0.72
     CreateTagHelper
    0.71
    OGND
    0.71
     transfieras
    0.71
     ProtoMessage
    0.70
    Act Density 1.030%

    No Known Activations