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

    Neuronpedia

    INDEX
    Explanations

    references to product conditions, damages, and repairs

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

    flaws or damage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.59
     Taktlose
    -0.59
     насељу
    -0.54
     otomatig
    -0.53
    nalités
    -0.52
     ſaid
    -0.52
     communiquez
    -0.50
    تقاوى
    -0.50
     الرياضيه
    -0.49
    OGND
    -0.48
    POSITIVE LOGITS
     damaged
    0.69
     damage
    0.65
     injuries
    0.57
    damaged
    0.57
     damages
    0.54
     defects
    0.53
     repairs
    0.51
     broken
    0.51
    damage
    0.51
     rusak
    0.50
    Act Density 0.097%

    No Known Activations