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

    Neuronpedia

    INDEX
    Explanations

    yesterday and tomorrow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    us
    0.92
    ,
    0.89
    ),
    0.84
    ;
    0.84
     dalam
    0.81
    ↵↵
    0.77
    ",
    0.77
    ↵
    0.77
     on
    0.77
    เป็น
    0.74
    POSITIVE LOGITS
    су
    0.89
    ве
    0.86
    ат
    0.86
    лог
    0.83
    ал
    0.80
    ек
    0.79
    ня
    0.79
    ем
    0.79
    пор
    0.78
    ер
    0.77
    Act Density 0.007%

    No Known Activations