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

    Neuronpedia

    INDEX
    Explanations

    button recessed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㶱
    0.45
    㒵
    0.44
    define
    0.44
    aiian
    0.44
    và
    0.44
    σει
    0.43
    arikat
    0.43
    are
    0.43
     nye
    0.43
    㤈
    0.42
    POSITIVE LOGITS
     С
    0.48
     athletes
    0.42
    Skills
    0.42
     ventilators
    0.41
     வெங்க
    0.41
     precision
    0.41
     skills
    0.41
     pharmacists
    0.41
     methotrexate
    0.41
     longevity
    0.40
    Act Density 0.003%

    No Known Activations