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

    Neuronpedia

    INDEX
    Explanations

    legal terminology and references related to policies and ownership

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

    or and all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kaynağından
    -0.53
     للمعارف
    -0.50
    الحياه
    -0.49
     diſt
    -0.47
     utafitiHapana
    -0.47
     незавершена
    -0.43
    <?
    -0.43
    әрмәләр
    -0.41
     encre
    -0.40
     itſelf
    -0.40
    POSITIVE LOGITS
    ConstraintMaker
    0.43
     Bowers
    0.42
     Johansen
    0.42
     apapun
    0.42
     Teufel
    0.41
    galkan
    0.41
    ThroughAttribute
    0.40
    koliv
    0.39
     numerus
    0.39
    tirol
    0.39
    Act Density 0.103%

    No Known Activations