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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     multitude
    -0.07
     lạ
    -0.07
     напрям
    -0.07
    acs
    -0.07
     irc
    -0.07
     програ
    -0.07
     INTO
    -0.06
     wave
    -0.06
    <Project
    -0.06
     Kingston
    -0.06
    POSITIVE LOGITS
     �
    0.06
    ')));↵
    0.06
    ;d
    0.06
    :title
    0.06
     arter
    0.06
    \uD
    0.06
     hurt
    0.06
    KERNEL
    0.06
    ())));↵
    0.06
    0.06
    Act Density 0.001%

    No Known Activations