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

    Neuronpedia

    INDEX
    Explanations

    introduces Spanish content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     percents
    0.25
    ﻬ
    0.24
    愊
    0.23
    ﾚ
    0.21
    кими
    0.21
    ្នែក
    0.21
    ုန်
    0.21
     operands
    0.21
    乆
    0.21
     forecasted
    0.21
    POSITIVE LOGITS
    <h2>
    0.32
    <strong>
    0.31
    *
    0.31
     How
    0.30
     Поэтому
    0.30
    <blockquote>
    0.30
     What
    0.28
     However
    0.27
    <b>
    0.27
    <h3>
    0.27
    Act Density 1.681%

    No Known Activations