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

    Neuronpedia

    INDEX
    Explanations

    hiccups, visualizations, electrodes, conjugation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     paradigma
    0.53
    Ņ
    0.50
     concetto
    0.49
    ancien
    0.48
     natürliche
    0.47
    Н
    0.46
     ideale
    0.46
     koncept
    0.46
    ÕES
    0.46
     خ
    0.46
    POSITIVE LOGITS
     连接
    0.43
     >
    0.41
     Fry
    0.41
     sə
    0.41
    циям
    0.40
    ).
    0.39
     Redmi
    0.39
     处理
    0.39
     关闭
    0.39
     Để
    0.39
    Act Density 0.007%

    No Known Activations