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

    Neuronpedia

    INDEX
    Explanations

    references to arXiv papers and related identifiers

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

    arXiv references

    np_acts-logits-general · gemini-2.0-flash

    arXiv papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jooq
    -0.95
    richTextPanel
    -0.82
    WriteBarrier
    -0.79
     larmes
    -0.76
     kaarangay
    -0.76
    kloped
    -0.75
    styleType
    -0.74
    ContentAsync
    -0.72
    CppMethod
    -0.72
     tartalomajánló
    -0.71
    POSITIVE LOGITS
    arXiv
    1.01
     arXiv
    0.64
     papers
    0.54
     arxiv
    0.54
     [
    0.50
     Arxiv
    0.47
    arxiv
    0.45
     Papers
    0.45
     bour
    0.45
     đề
    0.42
    Act Density 0.074%

    No Known Activations