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

    Neuronpedia

    INDEX
    Explanations

    historical dates and origins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     H
    0.39
     Yeast
    0.38
     Coordinates
    0.37
     Xue
    0.37
     facilité
    0.36
     água
    0.36
     Cell
    0.36
     Laplace
    0.36
     Patel
    0.36
    guien
    0.35
    POSITIVE LOGITS
     onwards
    0.64
    부터
    0.55
     onward
    0.51
     silam
    0.51
     وحتى
    0.49
     म्हणजेच
    0.47
    maar
    0.47
    लेकिन
    0.45
     (!)
    0.45
    并在
    0.42
    Act Density 0.064%

    No Known Activations