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

    Neuronpedia

    INDEX
    Explanations

    order

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iske
    -0.08
     Trem
    -0.07
    尚未
    -0.07
     Tro
    -0.07
    ﻱ
    -0.07
    ("+
    -0.07
     FAT
    -0.07
     xử
    -0.06
    MITTED
    -0.06
     latitude
    -0.06
    POSITIVE LOGITS
    鄫
    0.07
    widget
    0.07
    _goods
    0.07
    平稳
    0.07
    핳
    0.07
    cats
    0.07
    سئل
    0.06
    .rpm
    0.06
    mem
    0.06
    Person
    0.06
    Act Density 0.126%

    No Known Activations