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

    Neuronpedia

    INDEX
    Explanations

    finding extremes by comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лно
    0.38
     inversa
    0.36
    lau
    0.36
     solv
    0.35
     przes
    0.35
    सब
    0.35
     quanto
    0.34
    ༘
    0.34
    row
    0.34
    partner
    0.33
    POSITIVE LOGITS
     comparisons
    0.80
     Comparisons
    0.75
    Comparison
    0.75
     срав
    0.70
     сравнению
    0.69
     comparison
    0.69
    Compar
    0.68
     comparing
    0.68
     Comparison
    0.68
     сравни
    0.68
    Act Density 0.057%

    No Known Activations