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

    Neuronpedia

    INDEX
    Explanations

    descriptive language related to visual imagery and sensory experiences

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

    describing light, steam, or shine

    np_acts-logits-general · gemini-2.0-flash

    visual and atmospheric descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.84
    ſelves
    -0.75
     queſta
    -0.73
     myſelf
    -0.68
    ſelf
    -0.68
     الرياضيه
    -0.66
     Anſ
    -0.65
     queſto
    -0.63
    verwijspagina
    -0.61
     Seeder
    -0.61
    POSITIVE LOGITS
     crisp
    0.32
     glistening
    0.32
     low
    0.31
     zacht
    0.31
     shimmering
    0.31
     trembled
    0.30
    TextSpan
    0.30
     wrinkled
    0.30
    ial
    0.30
    cho
    0.30
    Act Density 0.219%

    No Known Activations