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

    Neuronpedia

    INDEX
    Explanations

    references and citations in academic or formal writing

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

    legal citations and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.55
    endregion
    -0.50
    ConstraintMaker
    -0.49
    ⤹
    -0.48
     betweenstory
    -0.48
     становника
    -0.48
     Cornwall
    -0.47
     Riviera
    -0.47
    ighborhood
    -0.47
    aarrggbb
    -0.46
    POSITIVE LOGITS
     cite
    1.17
     Cite
    0.72
    Cite
    0.71
     cited
    0.71
    Hentet
    0.66
     cites
    0.62
     citing
    0.61
    Autoritní
    0.55
     citar
    0.54
    cite
    0.54
    Act Density 0.001%

    No Known Activations