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

    Neuronpedia

    INDEX
    Explanations

    explaining how people speak

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Warum
    0.54
    滢
    0.52
    Почему
    0.50
    赐
    0.50
    갑습니다
    0.49
    关注
    0.48
    ویه
    0.48
    解码
    0.48
     изобра
    0.48
    评审
    0.48
    POSITIVE LOGITS
    0.57
     oil
    0.54
     chloroform
    0.53
     petroleum
    0.52
     nor
    0.47
     soybeans
    0.47
     files
    0.47
     chemicals
    0.46
     coal
    0.46
     elites
    0.46
    Act Density 0.002%

    No Known Activations