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

    Neuronpedia

    INDEX
    Explanations

    qzect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Manners
    0.67
     Schauspiel
    0.62
     หรือ
    0.60
     종합
    0.60
    โน
    0.59
     Ressourcen
    0.58
     দু
    0.57
     或
    0.57
     spielte
    0.57
     गेम
    0.57
    POSITIVE LOGITS
    tube
    0.60
     insist
    0.60
    🎋
    0.59
     исто
    0.59
     uart
    0.59
    ular
    0.58
     dess
    0.58
    🌇
    0.58
    ುತ್ತ
    0.57
     ingles
    0.57
    Act Density 0.000%

    No Known Activations