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

    Neuronpedia

    INDEX
    Explanations

    corporations, Sponsorships, Vintage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Victor
    0.46
     Victor
    0.42
    Articulation
    0.41
     Polyg
    0.41
    Hero
    0.39
     Barangay
    0.39
     Hero
    0.39
    INED
    0.39
    滾
    0.38
    Kent
    0.37
    POSITIVE LOGITS
     agendas
    0.47
     stealth
    0.45
     sponsorship
    0.44
     sponsorships
    0.44
     корпора
    0.41
    Corp
    0.41
     programs
    0.40
    corp
    0.40
     Mox
    0.40
     কর্প
    0.40
    Act Density 0.002%

    No Known Activations