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

    Neuronpedia

    INDEX
    Explanations

    checkout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onte
    -0.06
     Path
    -0.06
    룹
    -0.06
    有
    -0.06
     muster
    -0.06
    增加
    -0.06
    оряд
    -0.06
     '.')
    -0.06
    _middle
    -0.06
    ляють
    -0.06
    POSITIVE LOGITS
     approached
    0.07
     vacuum
    0.07
     застав
    0.07
    交通
    0.07
    -educated
    0.06
     checkout
    0.06
     sauna
    0.06
     suger
    0.06
     登
    0.06
    (conn
    0.06
    Act Density 0.001%

    No Known Activations