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

    Neuronpedia

    INDEX
    Explanations

    elements of cultural significance and local identities in texts

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

    locations and place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mot
    -0.38
    原始内容存档于
    -0.35
     tit
    -0.35
     force
    -0.35
     qual
    -0.34
    翻
    -0.34
    xc
    -0.34
     c
    -0.33
     kur
    -0.33
     tr
    -0.33
    POSITIVE LOGITS
     purpoſe
    0.62
     Paglinawan
    0.58
    ביוגרפיה
    0.57
     étoit
    0.53
     Мексичка
    0.52
    GEBURTS
    0.50
    rungsseite
    0.50
     pouvoit
    0.49
     poffible
    0.49
    étoit
    0.48
    Act Density 0.008%

    No Known Activations