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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating location or position

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

    words meaning inside or within

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obicei
    -0.59
     ویکی‌پدی
    -0.51
    地说道
    -0.51
     cib
    -0.50
    gels
    -0.49
     argint
    -0.49
    tanleria
    -0.49
    をかける
    -0.48
     EconPapers
    -0.48
    をかけ
    -0.48
    POSITIVE LOGITS
    dentro
    1.27
    Dentro
    1.25
     dentro
    1.23
     Dentro
    1.18
     dins
    0.67
     μέσα
    0.66
     adentro
    0.63
     inside
    0.63
    inside
    0.62
    Inside
    0.60
    Act Density 0.001%

    No Known Activations