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

    Neuronpedia

    INDEX
    Explanations

    start and end points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $\$
    0.61
     $\%
    0.60
     $\%$
    0.55
     $€
    0.52
     $\#
    0.50
     $[
    0.50
     $:=$
    0.50
     $\{
    0.48
     $>
    0.47
     $[-
    0.47
    POSITIVE LOGITS
     gathered
    0.70
    aligned
    0.68
    gathered
    0.66
     aligned
    0.62
     تجمع
    0.61
     alignment
    0.55
     gather
    0.52
    array
    0.51
     Gather
    0.51
     συγκ
    0.50
    Act Density 0.000%

    No Known Activations