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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    desktop
    -0.07
    ус
    -0.07
    Resume
    -0.07
    Ⲗ
    -0.07
    סק
    -0.07
    哈尔滨
    -0.07
    ential
    -0.07
    bundles
    -0.07
    קבוצות
    -0.07
    -m
    -0.07
    POSITIVE LOGITS
    (Array
    0.08
    쟁
    0.07
     =[
    0.07
     pimp
    0.07
    （笑
    0.07
    (let
    0.07
     Nico
    0.07
     China
    0.07
     Supporters
    0.07
    갉
    0.07
    Act Density 0.023%

    No Known Activations