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

    Neuronpedia

    INDEX
    Explanations

    listing items, stats, or qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    心态
    0.44
    ɰ
    0.40
    内地
    0.39
    ㄿ
    0.38
     INTERNAL
    0.38
    стоян
    0.38
    띄
    0.38
    oxidase
    0.37
    érieure
    0.37
    orsese
    0.37
    POSITIVE LOGITS
     functional
    0.39
     Physically
    0.39
     practical
    0.38
     pertin
    0.36
     constructive
    0.36
     clinically
    0.36
     Malin
    0.36
     cognitive
    0.35
     productive
    0.35
     informativa
    0.35
    Act Density 0.382%

    No Known Activations