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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lod
    -0.06
    pip
    -0.06
    >())↵
    -0.06
     Kö
    -0.06
    �
    -0.06
     Rebel
    -0.06
    ед
    -0.06
    avings
    -0.06
    coding
    -0.06
     بگیر
    -0.06
    POSITIVE LOGITS
     Awesome
    0.07
     awesome
    0.07
     mevcut
    0.07
     STL
    0.06
     paragraph
    0.06
     restaurant
    0.06
     �
    0.06
    造成
    0.06
    了
    0.06
    价值
    0.06
    Act Density 0.004%

    No Known Activations