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

    Neuronpedia

    INDEX
    Explanations

    the phrase "nearest" as it relates to rounding numbers

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

    rounding to the nearest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    spoiler
    -0.55
    Gabe
    -0.52
    devamını
    -0.51
     conflicted
    -0.50
     scol
    -0.50
     Hulk
    -0.50
    AuthContext
    -0.50
    arXiv
    -0.50
    olm
    -0.49
    Ivy
    -0.49
    POSITIVE LOGITS
     nearest
    2.03
    nearest
    1.99
     Nearest
    1.86
    Nearest
    1.77
     ближай
    0.91
     nearer
    0.87
     terdekat
    0.86
     najbli
    0.75
     closest
    0.63
     näch
    0.56
    Act Density 0.008%

    No Known Activations