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

    Neuronpedia

    INDEX
    Explanations

    references to specific institutions or publications

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

    institutions, brands, or events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.83
    ロウィン
    -0.82
    ſicht
    -0.79
    yarnpkg
    -0.76
     <=",
    -0.76
     Weiſe
    -0.75
     kasarigan
    -0.75
    <unused41>
    -0.75
    <unused14>
    -0.75
    [@BOS@]
    -0.74
    POSITIVE LOGITS
    ®
    0.37
     partner
    0.36
     brand
    0.33
    《
    0.31
     proudly
    0.30
     place
    0.29
    ,
    0.29
     tiết
    0.29
    web
    0.29
     Partnership
    0.29
    Act Density 0.009%

    No Known Activations