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

    Neuronpedia

    INDEX
    Explanations

    ISO safety standards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Gmail
    0.89
     Nonprofit
    0.89
     Gmail
    0.87
     Patreon
    0.84
     Craigslist
    0.83
     Yelp
    0.81
    Yahoo
    0.81
    Civ
    0.79
    🏘
    0.79
     Filmm
    0.79
    POSITIVE LOGITS
     safety
    1.33
     Safety
    1.33
     equipment
    1.32
     plant
    1.28
     Equipment
    1.28
     hazard
    1.26
     hazardous
    1.24
     criticality
    1.23
    Safety
    1.20
     Plant
    1.17
    Act Density 0.635%

    No Known Activations