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

    Neuronpedia

    INDEX
    Explanations

    //

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    些
    -0.07
    ᕦ
    -0.07
    े
    -0.07
    .shiro
    -0.07
    煟
    -0.07
     צריך
    -0.07
    ﻒ
    -0.07
    克
    -0.06
    有一
    -0.06
    sort
    -0.06
    POSITIVE LOGITS
     alignments
    0.07
    Near
    0.07
    _human
    0.07
    电视
    0.07
     Television
    0.07
     disbelief
    0.07
     GLenum
    0.07
    .*;
↵
↵
    0.07
    allax
    0.07
    ullan
    0.07
    Act Density 0.001%

    No Known Activations