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

    Neuronpedia

    INDEX
    Explanations

    finds something interesting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.94
    TER
    0.87
    i
    0.87
    itte
    0.81
    iidae
    0.80
    इद
    0.79
    这个问题
    0.76
    ぇ
    0.76
    मीडिया
    0.75
    不再
    0.74
    POSITIVE LOGITS
    лган
    0.89
     extensão
    0.87
    вается
    0.86
     sæ
    0.86
     coexist
    0.86
     gebied
    0.83
    ных
    0.81
     hva
    0.80
     forskellige
    0.80
     vâr
    0.79
    Act Density 0.000%

    No Known Activations