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

    Neuronpedia

    INDEX
    Explanations

    Technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     speculate
    -0.07
    aus
    -0.07
    /support
    -0.07
     aun
    -0.06
     TIMEOUT
    -0.06
     Judaism
    -0.06
    \common
    -0.06
    eping
    -0.06
    atz
    -0.06
    mq
    -0.06
    POSITIVE LOGITS
    ",{
    0.08
     دي
    0.08
    积极开展
    0.07
    ﻵ
    0.07
     Science
    0.07
    ヒ
    0.07
    安县
    0.07
    �
    0.07
    aptive
    0.07
    (Attribute
    0.07
    Act Density 0.060%

    No Known Activations