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

    Neuronpedia

    INDEX
    Explanations

    let

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (payload
    -0.07
    rewrite
    -0.07
    西甲
    -0.06
    绿水
    -0.06
    出して
    -0.06
    adaş
    -0.06
    Jordan
    -0.06
    .World
    -0.06
    wagon
    -0.06
    교회
    -0.06
    POSITIVE LOGITS
     �
    0.07
    先进
    0.07
    匆
    0.07
     polym
    0.07
    多元化
    0.07
     köln
    0.06
    .Objects
    0.06
     advantage
    0.06
    ﻹ
    0.06
     keen
    0.06
    Act Density 0.008%

    No Known Activations