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

    Neuronpedia

    INDEX
    Explanations

    descriptions of the physical condition and details of items, particularly focusing on flaws and imperfections

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

    Imperfections or damages

    np_acts-logits-general · gemini-2.0-flash

    physical imperfections and damage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.73
    tonode
    -0.60
    marshaller
    -0.60
    lankton
    -0.52
     Sech
    -0.51
     exclusives
    -0.49
    PageModule
    -0.49
    期刊论文
    -0.49
     internetowa
    -0.48
    prnewswire
    -0.48
    POSITIVE LOGITS
     scratches
    1.25
     cracks
    1.08
     scratch
    0.97
     dents
    0.94
     scu
    0.93
     crack
    0.91
     cracked
    0.90
     blemishes
    0.88
     damage
    0.86
     marks
    0.86
    Act Density 0.185%

    No Known Activations