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

    Neuronpedia

    INDEX
    Explanations

    lists describing choices and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SupportPackage
    0.42
     गंभीर
    0.41
     உயரம்
    0.40
     nejen
    0.40
     yli
    0.39
    奀
    0.39
    ientôt
    0.39
    Tambah
    0.39
     médicament
    0.38
    वरिश
    0.38
    POSITIVE LOGITS
     tracking
    0.44
     seemingly
    0.43
     preserving
    0.41
     loyal
    0.41
     synchronized
    0.40
     captains
    0.40
     heroic
    0.40
     grouping
    0.39
     strategic
    0.39
     Maintaining
    0.39
    Act Density 0.015%

    No Known Activations