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

    Neuronpedia

    INDEX
    Explanations

    from now on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sonaro
    0.39
    ottesville
    0.38
     stato
    0.37
     terdapat
    0.37
    ژه
    0.37
    iggio
    0.37
     мм
    0.36
     ক্ল
    0.36
    леко
    0.36
     отвер
    0.36
    POSITIVE LOGITS
     henceforth
    1.27
    今後
    1.22
    以后
    1.09
     future
    1.05
     hereafter
    1.02
     भविष्य
    0.99
     futuras
    0.97
    以後
    0.96
    future
    0.96
     앞으로
    0.93
    Act Density 0.103%

    No Known Activations