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

    Neuronpedia

    INDEX
    Explanations

    references to academic papers or research articles

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

    in this paper, we

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Zul
    -0.39
    ContextCompat
    -0.37
    <bos>
    -0.36
    transit
    -0.36
    costo
    -0.35
     tanı
    -0.35
     alivio
    -0.35
     Schmitz
    -0.35
    Connell
    -0.35
    MergeFrom
    -0.35
    POSITIVE LOGITS
     papers
    1.11
     paper
    1.08
     Papers
    1.07
     Paper
    0.99
     PAPERS
    0.95
    Paper
    0.95
    Papers
    0.94
     PAPER
    0.93
    papers
    0.90
    paper
    0.89
    Act Density 0.037%

    No Known Activations