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

    Neuronpedia

    INDEX
    Explanations

    research-related phrases that indicate reporting or presenting findings

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

    Academic reports/discussions

    np_acts-logits-general · gemini-2.0-flash

    presenting research findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.77
     ویکی‌پدی
    -0.74
     estekak
    -0.70
    tagHelperRunner
    -0.67
    StoryboardSegue
    -0.65
     kasarigan
    -0.65
    хьтан
    -0.65
    Хьажоргаш
    -0.63
    exitRule
    -0.63
     oprot
    -0.61
    POSITIVE LOGITS
     operation
    0.33
     extremely
    0.33
     opdracht
    0.30
     use
    0.29
     exceptionally
    0.29
     another
    0.29
     located
    0.29
     leading
    0.29
     the
    0.28
     medium
    0.28
    Act Density 0.646%

    No Known Activations