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

    Neuronpedia

    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ആരംഭ
    0.57
    ಬ್ಬಳ್ಳಿ
    0.57
     Tige
    0.54
     OHIO
    0.54
    \">\
    0.53
    ParkingSpot
    0.52
    স্তন
    0.52
    す
    0.51
    刈
    0.51
     الدين
    0.50
    POSITIVE LOGITS
     冷
    0.70
     tenderness
    0.66
     Rates
    0.64
     Permits
    0.63
     Affect
    0.62
     abusers
    0.62
    滥
    0.62
    洁
    0.61
     Архи
    0.61
     Warnings
    0.61
    Act Density 0.001%

    No Known Activations