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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter 's' in various contexts

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

    Plural form, often ending in "s"

    np_acts-logits-general · gemini-2.0-flash

    letter s

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.85
     leaſt
    -0.85
     raiſ
    -0.85
     ―――――
    -0.82
     preſent
    -0.80
     viſ
    -0.79
    neſs
    -0.79
     tranſ
    -0.78
     myſelf
    -0.78
     themſelves
    -0.77
    POSITIVE LOGITS
    ⓧ
    0.93
    thenReturn
    0.72
    -------------</
    0.66
     للمعارف
    0.63
     s
    0.61
    ๆ
    0.60
     cardíaca
    0.60
    НИК
    0.57
    cobacterium
    0.56
    urlpatterns
    0.55
    Act Density 0.281%

    No Known Activations