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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    禅
    0.64
    禪
    0.59
    jima
    0.56
     Asha
    0.55
     Amaya
    0.54
     আগুন
    0.52
    ברה
    0.51
    Ǧ
    0.51
    جیب
    0.50
     آتش
    0.50
    POSITIVE LOGITS
     Lincolnshire
    0.64
     Salford
    0.64
     LOFT
    0.62
     Ingle
    0.60
     sain
    0.59
     Cornwall
    0.59
     Loft
    0.57
     обре
    0.57
     Yarm
    0.57
    Nullable
    0.56
    Act Density 0.001%

    No Known Activations