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

    Neuronpedia

    INDEX
    Explanations

    references to treasures and valuable items

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

    treasure and valuables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ExtendWith
    -0.50
     Rogan
    -0.49
    urlpatterns
    -0.48
     amongst
    -0.47
     Shades
    -0.47
    Shades
    -0.46
    atimes
    -0.46
     فريبيس
    -0.46
    Хьажоргаш
    -0.45
    okovic
    -0.44
    POSITIVE LOGITS
     TREAS
    1.20
     treasure
    1.18
    Treasure
    1.11
     treasury
    1.10
    treasure
    1.09
     Treasure
    1.08
     trésor
    1.07
     Treasures
    1.07
     treasures
    1.06
     tesoro
    0.99
    Act Density 0.015%

    No Known Activations