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

    Neuronpedia

    INDEX
    Explanations

    punctuation and "as"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    焱
    -0.07
    寵
    -0.07
     -->↵
    -0.07
     chó
    -0.07
    🏆
    -0.07
    Att
    -0.07
    �
    -0.07
     الإنترنت
    -0.07
    loyd
    -0.06
     çocuğu
    -0.06
    POSITIVE LOGITS
     Mother
    0.07
    Grace
    0.06
    光滑
    0.06
    枧
    0.06
    一向
    0.06
     البر
    0.06
    HBoxLayout
    0.06
    .classes
    0.06
    Vision
    0.06
    傍晚
    0.06
    Act Density 0.083%

    No Known Activations