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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     breathe
    -0.08
    олько
    -0.08
     время
    -0.08
    (rgb
    -0.07
    完成了
    -0.07
    .responses
    -0.07
     consolidation
    -0.07
    niej
    -0.07
    落入
    -0.07
     cấp
    -0.07
    POSITIVE LOGITS
    chat
    0.07
    깉
    0.07
    azi
    0.07
     Mobil
    0.07
    🏍
    0.06
    auga
    0.06
    �
    0.06
     anime
    0.06
     Steph
    0.06
    二手车
    0.06
    Act Density 0.001%

    No Known Activations