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

    Neuronpedia

    INDEX
    Explanations

    describing a process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anlamı
    -0.08
    _beta
    -0.07
    请注意
    -0.07
    ArrayOf
    -0.07
    摛
    -0.07
    皦
    -0.06
     默认
    -0.06
    ﻕ
    -0.06
     puzzled
    -0.06
    Advisor
    -0.06
    POSITIVE LOGITS
    บร
    0.06
    حافظ
    0.06
     perf
    0.06
    ft
    0.06
    党建
    0.06
    效果图
    0.06
     pathlib
    0.06
    乳腺
    0.06
     станет
    0.06
     trips
    0.06
    Act Density 0.065%

    No Known Activations