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

    Neuronpedia

    INDEX
    Explanations

    occurrences of asterisks, which might represent placeholders or comments in code

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

    documentation tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.68
    IUrlHelper
    -0.60
     AssemblyCompany
    -0.59
    -0.58
    पया
    -0.57
    ✨:
    -0.57
     kasarigan
    -0.56
    EndContext
    -0.56
    脚注の使い方
    -0.54
    istir
    -0.52
    POSITIVE LOGITS
    GHIJKLM
    0.39
     sometimes
    0.35
     immediately
    0.34
    Хьажоргаш
    0.33
    CodeAttribute
    0.32
     now
    0.32
    omeness
    0.31
     which
    0.30
     assolu
    0.30
    Immediately
    0.29
    Act Density 0.011%

    No Known Activations