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

    Neuronpedia

    INDEX
    Explanations

    the actual attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     их
    0.95
     їх
    0.85
     sua
    0.85
    其
    0.84
     его
    0.83
     jų
    0.83
     എത്ത
    0.82
     Phenomena
    0.82
     የመ
    0.82
     seva
    0.82
    POSITIVE LOGITS
     ecology
    0.72
     marketing
    0.67
     freshly
    0.66
     design
    0.63
     upkeep
    0.63
    marketing
    0.63
    packaging
    0.60
    specification
    0.60
    arming
    0.59
     packaging
    0.58
    Act Density 0.543%

    No Known Activations