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

    Neuronpedia

    INDEX
    Explanations

    Experts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Small
    -0.07
     reaches
    -0.06
     Accred
    -0.06
    갑
    -0.06
     ευ
    -0.06
     ober
    -0.06
     ROT
    -0.06
    BTN
    -0.06
    اسه
    -0.06
    <Customer
    -0.06
    POSITIVE LOGITS
    (:,:,
    0.07
     yeterli
    0.06
     Boris
    0.06
     Heap
    0.06
    ﻨ
    0.06
     osob
    0.06
    .exe
    0.06
    (KERN
    0.06
    něte
    0.06
    .......
    0.06
    Act Density 0.065%

    No Known Activations