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

    Neuronpedia

    INDEX
    Explanations

    cannot replace or substitute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    1.06
    และ
    1.06
     एवं
    1.05
     및
    1.05
     и
    1.00
    both
    0.99
     और
    0.98
    및
    0.98
     及
    0.96
    এবং
    0.96
    POSITIVE LOGITS
     nor
    1.88
     anymore
    1.53
     either
    1.37
     atau
    1.36
    nor
    1.34
     Nor
    1.27
     ataupun
    1.27
     eller
    1.25
     või
    1.25
    Nor
    1.24
    Act Density 0.120%

    No Known Activations