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

    Neuronpedia

    INDEX
    Explanations

    words related to comparisons and contrasts between groups or entities

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

    Preceding the word "two."

    np_acts-logits-general · gemini-2.0-flash

    other two, first two, latter two

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     allemaal
    -0.63
     للاسماء
    -0.56
    tifact
    -0.56
     otomatig
    -0.56
     CreateTagHelper
    -0.55
    Արտաքին
    -0.53
     vieles
    -0.52
    wnież
    -0.52
    gorov
    -0.52
    todas
    -0.50
    POSITIVE LOGITS
     two
    2.88
    two
    2.53
     deux
    2.31
    Two
    2.13
     Two
    1.99
     TWO
    1.98
    TWO
    1.98
     zwei
    1.97
     dwóch
    1.93
    两个
    1.91
    Act Density 0.903%

    No Known Activations