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

    Neuronpedia

    INDEX
    Explanations

    chemical weapons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     показателей
    1.85
     दिसंबर
    1.73
     suburbs
    1.70
    隨著
    1.68
     abbreviations
    1.68
     tony
    1.67
     environs
    1.66
     способы
    1.66
     godziny
    1.65
     обучение
    1.64
    POSITIVE LOGITS
    }">${
    2.04
    िटी
    1.98
    页面存档备份
    1.91
     Produto
    1.83
    !--
    1.82
    WebpackPlugin
    1.77
    줌
    1.75
    screw
    1.74
    కి
    1.74
    édi
    1.70
    Act Density 0.000%

    No Known Activations