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

    Neuronpedia

    INDEX
    Explanations

    references to academic papers and related terms

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

    "paper" as a research document

    np_acts-logits-general · gemini-2.0-flash

    in this paper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Clifton
    -0.49
    mitz
    -0.48
    MergeFrom
    -0.48
     Connell
    -0.48
    stalgia
    -0.47
    ชม
    -0.46
     cruzar
    -0.45
     perigo
    -0.44
     McGrath
    -0.44
    tux
    -0.44
    POSITIVE LOGITS
     paper
    1.21
     Paper
    1.19
     PAPER
    1.18
    Paper
    1.18
     Papier
    1.05
    PAPER
    1.04
     Papers
    1.02
    paper
    1.02
     papers
    1.02
     PAPERS
    0.96
    Act Density 0.076%

    No Known Activations