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

    Neuronpedia

    INDEX
    Explanations

    references to memory and the lasting impact of people or events

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

    permanence or lasting a long time

    np_acts-logits-general · gemini-2.0-flash

    forever and always

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.62
    .*")]
    -0.60
    OGND
    -0.58
    {{/
    -0.56
    ValueStyle
    -0.54
    */),
    -0.54
    PyExc
    -0.53
    +#+
    -0.52
    تقاوى
    -0.51
     يتيمه
    -0.50
    POSITIVE LOGITS
     forever
    1.08
     Forever
    0.95
    forever
    0.92
     FOREVER
    0.90
    Forever
    0.89
     навсегда
    0.85
     eternally
    0.79
    永远
    0.75
     memories
    0.70
     eterna
    0.70
    Act Density 0.118%

    No Known Activations