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

    Neuronpedia

    INDEX
    Explanations

    dynamic programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     و
    0.50
     व
    0.47
    la
    0.46
    ਦਾ
    0.45
     Frühstück
    0.45
     Majesty
    0.44
    три
    0.44
     Changing
    0.43
     Sculpture
    0.42
     Sometimes
    0.42
    POSITIVE LOGITS
     completar
    0.52
    }.
    0.50
     ungraded
    0.50
     چاہے
    0.50
     जाइए
    0.49
    अगर
    0.48
    រយៈពេល
    0.48
    इये
    0.48
     प्रक्रिया
    0.47
     российских
    0.47
    Act Density 0.000%

    No Known Activations