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

    Neuronpedia

    INDEX
    Explanations

    small

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    覚
    -0.07
    ве
    -0.07
    �
    -0.06
     Luo
    -0.06
    ajes
    -0.06
    /animate
    -0.06
    ModelAttribute
    -0.06
    <Func
    -0.06
     Кроме
    -0.06
    TINGS
    -0.06
    POSITIVE LOGITS
    owell
    0.07
    (sk
    0.07
    (toolbar
    0.07
     battery
    0.07
    pai
    0.06
    AMY
    0.06
    .rb
    0.06
    展示
    0.06
    .den
    0.06
     Đại
    0.06
    Act Density 0.010%

    No Known Activations