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

    Neuronpedia

    INDEX
    Explanations

    button onclick or id

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     concetto
    0.57
    經濟
    0.51
     economic
    0.50
     Year
    0.50
     dato
    0.50
     অর্থনৈতিক
    0.50
     nuovo
    0.47
    قتصاد
    0.47
     głos
    0.47
     голосо
    0.46
    POSITIVE LOGITS
    බා
    0.47
    ians
    0.46
    zigzag
    0.43
    enses
    0.43
    olines
    0.42
    %.
    0.41
    セプト
    0.41
    ",'
    0.41
    Cam
    0.41
    zoa
    0.41
    Act Density 0.002%

    No Known Activations