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

    Neuronpedia

    INDEX
    Explanations

    reason or purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    цията
    0.88
    ة
    0.87
    ori
    0.79
     tiver
    0.77
     necessariamente
    0.77
    Whether
    0.76
    कार्य
    0.75
    りで
    0.74
    bei
    0.74
    vili
    0.74
    POSITIVE LOGITS
     use
    1.91
     purposes
    1.55
     posterity
    1.46
     sale
    1.45
     uso
    1.41
     inclusion
    1.38
     Use
    1.33
     easier
    1.29
     यूज
    1.20
     upotre
    1.20
    Act Density 0.434%

    No Known Activations