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

    Neuronpedia

    INDEX
    Explanations

    performance, stakes, revenue, improverishment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     o
    0.44
     ro
    0.44
    alk
    0.44
     j
    0.43
    ൈ
    0.43
     i
    0.43
    切割
    0.41
     hogy
    0.40
    önig
    0.40
     esempio
    0.39
    POSITIVE LOGITS
     outperforms
    0.45
     outperformed
    0.45
     impoverished
    0.43
     hypersurfaces
    0.43
     outperform
    0.42
    щены
    0.42
     underdeveloped
    0.41
     quarterfinals
    0.41
     поверхности
    0.41
     aperiam
    0.41
    Act Density 0.001%

    No Known Activations