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

    Neuronpedia

    INDEX
    Explanations

    references to historical and cultural groups and their interactions

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

    historical context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ฝ
    -0.33
     entornos
    -0.33
     Leiter
    -0.32
    下的
    -0.32
    Einzel
    -0.31
     his
    -0.30
     prendas
    -0.30
    Flo
    -0.29
     langues
    -0.29
     elementary
    -0.29
    POSITIVE LOGITS
    themselves
    0.75
    Abitanti
    0.74
    帖最后由
    0.70
     betweenstory
    0.68
     themselves
    0.67
    AndEndTag
    0.65
     Italijanski
    0.65
    Архівовано
    0.65
    StoryboardSegue
    0.64
    ंदीखरीदारी
    0.64
    Act Density 0.338%

    No Known Activations