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

    Neuronpedia

    INDEX
    Explanations

    colon followed by the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ቶችን
    0.46
    ሮችን
    0.42
    ларды
    0.42
     buradan
    0.42
    новні
    0.41
    ινων
    0.39
    дных
    0.39
     dette
    0.39
     denne
    0.38
    ሎችን
    0.38
    POSITIVE LOGITS
    The
    2.08
     The
    1.93
    the
    1.82
     THE
    1.74
    THE
    1.66
     the
    1.65
    nThe
    1.54
    sthe
    1.32
     দ্য
    1.27
    thebetter
    1.05
    Act Density 0.966%

    No Known Activations