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

    Neuronpedia

    INDEX
    Explanations

    years and dates

    np_acts-logits-general · gemini-2.5-flash-lite

    information current as of late 2023 / early 2024

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ot
    0.91
    for
    0.91
     for
    0.90
    is
    0.88
    er
    0.77
    ic
    0.73
     l
    0.70
    us
    0.69
    el
    0.69
     of
    0.68
    POSITIVE LOGITS
    ０
    0.70
    ljena
    0.65
    ૦
    0.63
    Ⲕ
    0.59
    。</
    0.55
    ﻙ
    0.55
    лия
    0.55
    はもちろん
    0.54
    Penumpang
    0.54
    .。
    0.53
    Act Density 0.506%

    No Known Activations