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

    Neuronpedia

    INDEX
    Explanations

    massive diverse datasets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     assassination
    0.47
     communément
    0.43
     Amaz
    0.42
     famous
    0.41
     monetization
    0.41
     आपल्याला
    0.41
     fondness
    0.41
     〔
    0.40
     incroyable
    0.40
    Foto
    0.39
    POSITIVE LOGITS
     Broadband
    0.45
    gll
    0.43
    orna
    0.42
     balances
    0.42
     Resilience
    0.41
    ालय
    0.40
     घंटों
    0.40
    lccc
    0.40
    uada
    0.40
    orent
    0.40
    Act Density 0.008%

    No Known Activations