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

    Neuronpedia

    INDEX
    Explanations

    finding the root or target

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ആദ്യം
    0.41
     insist
    0.41
     bifur
    0.41
     turmoil
    0.40
     Thoreau
    0.40
     insisting
    0.40
    ourses
    0.38
     voltar
    0.38
     Dickens
    0.38
    horizon
    0.38
    POSITIVE LOGITS
    均匀
    0.39
    Congrats
    0.38
     congratulations
    0.38
    Congratulations
    0.38
     absence
    0.37
     يا
    0.37
     ഇത്
    0.36
     ZERO
    0.35
     currentGame
    0.35
    これは
    0.35
    Act Density 0.002%

    No Known Activations